SMT (Statistical Machine Translation) & Chatbots

Notes:

Statistical machine translation is a type of machine translation that uses statistical models to automatically translate text or speech from one language to another. It is based on the idea that the best way to translate a piece of text is to find the translation that is most likely to have produced the original text, given the statistical patterns of the languages involved.

Statistical machine translation is related to chatbots in that it can be used to enable chatbots to communicate with users in different languages. For example, a chatbot that uses statistical machine translation could be programmed to understand and respond to user input in multiple languages, allowing it to communicate with a wider audience. Chatbots that use statistical machine translation can be particularly useful in customer service scenarios, where they can be used to assist users who speak different languages or to translate between languages in real-time.

Neural machine translation (NMT) is a type of machine translation that uses artificial neural networks to translate text or speech from one language to another. NMT systems are trained on large datasets of human-translated text, and use this training data to learn the statistical patterns and relationships between the source and target languages.

To translate a piece of text, an NMT system first encodes the source text into a numerical representation, which is then processed by a neural network. The neural network consists of multiple layers of interconnected “neurons,” which are used to analyze and interpret the input data. The output of the neural network is then decoded back into the target language, producing a translation of the original text.

One of the key advantages of NMT is that it can handle the complexity and variability of natural languages more effectively than other machine translation approaches. NMT systems can handle idiomatic expressions, word play, and other language nuances that are difficult for other machine translation methods to handle. As a result, NMT is often considered to be a more accurate and effective way to translate text than other methods.

Wikipedia:

• Statistical machine translation

References:

• Advanced Applications of Natural Language Processing for Performing Information Extraction (2015)
• Routledge Encyclopedia of Translation Technology (2015)
• Handbook of Natural Language Processing and Machine Translation (2011)

See also:

100 Best GitHub: Machine Translation | EBMT (Example-Based Machine Translation) & Dialog Systems | RBMT (Rule-Based Machine Translation) & Dialog Systems

---

Response selection with topic clues for retrieval-based chatbots
Y Wu, Z Li, W Wu, M Zhou – Neurocomputing, 2018 – Elsevier
… A typical framework of retrieval based chatbot [3] is that a chatbot first obtains several response candidates with a search engine, and then employs a text similarity model to calculate the … Generation based chatbots employ statistical machine translation techniques [18 …

Scalable sentiment for sequence-to-sequence chatbot response with performance analysis
CW Lee, YS Wang, TY Hsu, KY Chen… – … , Speech and Signal …, 2018 – ieeexplore.ieee.org
… sentiment coherence 1 and 2 (COH1, COH2) specially for chatbots, which give … and Eric Atwell, “Different measurements metrics to evaluate a chatbot system,” in … Learning phrase representations using rnn encoder-decoder for statistical machine translation,” arXiv preprint arXiv …

Chitty-Chitty-Chat Bot: Deep Learning for Conversational AI.
R Yan – IJCAI, 2018 – ijcai.org
… The promising user data indicate impressive popularity of the chatbot service … We will summarize the problem formulation and data collection for chatbots, and give an … the feasibility of conducting short text conversation by using statistical machine translation (SMT) techniques …

A knowledge-grounded neural conversation model
M Ghazvininejad, C Brockett, MW Chang… – Thirty-Second AAAI …, 2018 – aaai.org
… However, these models have been mostly applied to casual scenarios (eg, as “chatbots”) and have yet to demonstrate they can serve in more … Introduction Recent work has shown that conversational chatbot mod- els can be trained in an end-to-end and completely data- driven …

Moon IME: neural-based chinese pinyin aided input method with customizable association
Y Huang, Z Li, Z Zhang, H Zhao – Proceedings of ACL 2018, System …, 2018 – aclweb.org
… 2016. Connecting phrase based statistical machine translation adaptation. In CoLING, pages 3135–3145 … 2017. Sequential matching network: A new architecture for multi-turn response selection in retrieval-based chatbots. In ACL, pages 496–505 …

Production Ready Chatbots: Generate if not Retrieve
A Tammewar, M Pamecha, C Jain, A Nagvenkar… – Workshops at the Thirty …, 2018 – aaai.org
… Cherry, and Dolan treating generation of conversa- tional dialogue as a statistical machine translation problem … was trained on a rela- tively smaller vocabulary for a chatbot.This leads … have presented a hybrid approach to create robust pro- duction ready closed domain chatbots …

Hierarchical recurrent attention network for response generation
C Xing, Y Wu, W Wu, Y Huang, M Zhou – Thirty-Second AAAI Conference on …, 2018 – aaai.org
… A common practice of building a chatbot is to train a response generation model within … we study multi-turn response generation for open domain conversation in chatbots in which … are the first who apply the hi- erarchical attention technique to response generation in chat- bots …

Lingke: A fine-grained multi-turn chatbot for customer service
P Zhu, Z Zhang, J Li, Y Huang, H Zhao – arXiv preprint arXiv:1808.03430, 2018 – arxiv.org
… Traditional chatbots usually need a mass of human dialogue data, especially when using super- vised machine … Learning phrase representations using RNN encoder-decoder for statistical machine translation … Supera- gent: A customer service chatbot for e-commerce websites …

User adaptive chatbot for mitigating depression
P Kataria, K Rode, A Jain, P Dwivedi… – International Journal of …, 2018 – acadpubl.eu
… Chatbots tend to fail when encountered with an unknown state- ment … A Chatbot for Psychiatric Counseling in Mental Healthcare Service Based on Emotional Dialogue Analysis … Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation …

Ruber: An unsupervised method for automatic evaluation of open-domain dialog systems
C Tao, L Mou, D Zhao, R Yan – Thirty-Second AAAI Conference on Artificial …, 2018 – aaai.org
… “I don’t know,”—which appears frequently in the training set (Li et al. 2015)—may also fit the query, but it does not make much sense in a commercial chatbot.1 The observation implies that a groundtruth alone is insufficient for the evaluation of open-domain dialog systems …

On evaluating and comparing conversational agents
A Venkatesh, C Khatri, A Ram, F Guo… – arXiv preprint arXiv …, 2018 – pdfs.semanticscholar.org
… have been used in both the MT (Gupta et al., 2015; Albrecht and Hwa, 2007) and chatbot domains (Lowe et … Such models can be components of a framework which compares chatbots, training them can also be a … Findings of the 2011 workshop on statistical machine translation …

Testing service oriented architectures using stateful service visualization via machine learning
HF Eni?er, A Sen – Proceedings of the 13th International Workshop on …, 2018 – dl.acm.org
… is transformed to sequence I am fine. Sequence-to-sequence models were previously employed in prob- lems requiring to consider whole history of input such as language translation [32] or automatic chat-bot creation [37, 38] and demon- strated successful results …

A survey of machine learning for big code and naturalness
M Allamanis, ET Barr, P Devanbu… – ACM Computing Surveys …, 2018 – dl.acm.org
… Con- sider the problem of automatically generating comments that describe code, which can be formal- ized as a machine translation problem from code to text. Statistical machine translation approaches learn from an aligned corpus …

The machine poetry generator imitating Du Fu’s styles
K Wang, J Tian, R Gao, C Yao – 2018 International Conference …, 2018 – ieeexplore.ieee.org
… Rule-based templates, genetic algorithms, statistical machine translation and summarization method are widely used to generate poems. Along with the rapid growth of machine learning techniques [16-18], the Chatbot XiaoIce produced by Microsoft could be able to generate …

Conversational model adaptation via KL divergence regularization
J Li, P Luo, F Lin, B Chen – Thirty-Second AAAI Conference on Artificial …, 2018 – aaai.org
… Specifically, for the building of a new chatbot, it leverages not only a lim- ited … words, chat- bot users may ask similar questions to the two chatbots from related … Because the basic frameworks of conversational models come from statistical machine translation, we include it in this …

Encoding emotional information for sequence-to-sequence response generation
YH Chan, AKF Lui – … on Artificial Intelligence and Big Data …, 2018 – ieeexplore.ieee.org
… The approach is essentially the same for response generation in chatbots that the … An emotional chatbot is a conversational agent that is conditioned to generate … et al., “Learning Phrase Representations using RNN Encoder- Decoder for Statistical Machine Translation,” arXiv [cs …

Out-of-domain detection method based on sentence distance for dialogue systems
KJ Oh, DK Lee, C Park, YS Jeong… – … Conference on Big …, 2018 – ieeexplore.ieee.org
… accuracy of the out-of-domain detection(OOD) method, and we apply this method to develop a chatbot system for … Therefore, various applications of NLU and natural language generation(NLG) utilize a language model such as statistical machine translation (SMT) …

TrumpBot: Seq2Seq with Pointer Sentinel Model
F Zivkovic, D Chen – 2018 – pdfs.semanticscholar.org
… Lastly, the chatbot utilized GloVE vectors as distributed word embeddings in order to gain semantic understanding of the text [17] … “Learning phrase representations using RNN encoder-decoder for statistical machine translation”. In: arXiv preprint arXiv:1406.1078 (2014) …

Chinese pinyin aided IME, input what you have not keystroked yet
Y Huang, H Zhao – arXiv preprint arXiv:1809.00329, 2018 – arxiv.org
… 2014. Learning phrase representations using RNN encoder-decoder for statistical machine translation … Lsequential matching network: A new architecture for multi-turn response selection in retrieval-based chatbots … Lingke: A fine-grained multi-turn chatbot for customer service …

Proceedings of the 13th Conference of the Association for Machine Translation in the Americas (Volume 2: User Papers)
J Campbell, A Yanishevsky, J Doyon… – Proceedings of the 13th …, 2018 – aclweb.org
… New topics presented this year include: automatic conversion of one language variation to another, integration of MT into chatbots, and automatic translation of … 223 Leveraging Data Resources for Cross-Linguistic Information Retrieval Using Statistical Machine Translation …

Modern Chatbot Systems: A Technical Review
AS Lokman, MA Ameedeen – Proceedings of the Future Technologies …, 2018 – Springer
… Referring to Table 1, it is clear that modern chatbots are 90% similar in term … F., Schwenk, H., Bengio, Y.: Learning phrase representations using RNN encoder-decoder for statistical machine translation … F., Tan, C., Duan, C., Zhou, M.: SuperAgent: a customer service chatbot for e …

Al-Chatbot: Elderly Aid
G Tascini – Proceedings on the International Conference on …, 2018 – search.proquest.com
… Current chatbots are in difficulty facing these tasks and overcome it by introducing Deep L NN … In this way, we created the premises for building our intelligent chatbot with the help a … Learning phrase representations using RNN encoder-decoder for statistical machine translation …

Implementing ChatBots using Neural Machine Translation techniques
A Nuez Ezquerra – 2018 – upcommons.upc.edu
… main goal of this project is to apply to generative-based conversational agents (chat- bots) two encoder … First, this section defines the area which studies and develops chatbot models, Natural Language … Chatbots belong to the area of NLP given the importance of their ability to …

Experimental research on encoder-decoder architectures with attention for chatbots
MR Costa-jussà, Á Nuez, C Segura – Computación y Sistemas, 2018 – cys.cic.ipn.mx
… Experimental Research on Encoder-Decoder Architectures with Attention for Chatbots 1237 … a couple of recently proposed attention mechanisms into the chatbot application … Learning phrase representations using RNN encoder-decoder for statistical machine translation …

A Survey on Chatbot Implementation in Customer Service Industry through Deep Neural Networks
M Nuruzzaman, OK Hussain – 2018 IEEE 15th International …, 2018 – ieeexplore.ieee.org
… Fig 1 Taxonomy of Chatbot Application i. Goal-based Chatbot Goal-based chatbots are classified based on the primary goal aim to achieve … iii. Service-based Chatbot Service-based chatbots are classified based on facilities provides to the customer …

Auto-Dialog Systems: Implementing Automatic Conversational Man-Machine Agents by Using Artificial Intelligence & Neural Networks
A Bala, T Padmaja, GKD Gopisettry – chsd-theresacollege.net
… To Sequence model introduced in Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation has since … [1] Chatbots: An Introduction … Easy Guide To Making Your Own, by Oisin Muldowney [2] Beginner’s guide to build chatbot using api.ai …

Deep Learning for Chatbots
VA Bhagwat – 2018 – scholarworks.sjsu.edu
… each input word, we are not able to capture the relationship between them, which is the essence Page 29. DEEP LEARNING FOR CHATBOTS 28 for our chatbot. Word embedding is a technique to capture the relationship between words. We first decide …

English to Kurdish Rule-based Machine Translation System
KM Kaka-Khan – 2018 – journals.uhd.edu.iq
… His research interest area include: Natural Language Processing, MT, Chatbot, and Information Security. REFERENCES [1] FH Khorshid … [8] PF Brown, VJD Pietra, SAD Pietra and RL Mercer. The mathematics of statistical machine translation: Parameter estimation …

Comparative Study of Topology and Feature Variants for Non-Task-Oriented Chatbot using Sequence to Sequence Learning
G Dzakwan, A Purwarianti – 2018 5th International Conference …, 2018 – ieeexplore.ieee.org
… Available: https://chatbotslife.com/nlp-nlu- nlg-and-how-chatbots-work-dd7861dfc9df … Xu, Z. Liu, Y. Guo, V. Sinha, R. Akkiraju, “A New Chatbot for Customer … Y. Bengio, ”Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation”, The 2014 …

Chatbot for Education System
R Nanaware – International Journal Of Emerging Technology …, 2018 – aspirepublishers.com
… The performance of statistical machine translation system is empirically found to improve by using the conditional … Nikita Hatwar “chat bot for marketing field named as AI based chat bot.”In 2016 [3] Y. Wu, G. Wang, W. Li and Z. Li, “Automatic Chatbot Knowledge Acquisition from …

Making Chatbots Better by Training on Less Data
RK Csaky, G Recski – researchgate.net
… Related to these issues is the evaluation of open-domain chatbots … 2014. Learning phrase representations using rnn encoder-decoder for statistical machine translation … Richárd Csáky. 2017. Deep learning based chatbot models …

A Virtual Chatbot for ITSM Application
S Raut – Asian Journal For Convergence In Technology …, 2018 – asianssr.org
… Chatbots that are developed using deep learning, mostly use a certain variant of sequence … [6] Bayu Setiaji, Ferry Wahyu Wibowo, “Chatbot Using A … Yoshua Bengio, “Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation”, CoRR abs …

Hybridization and Application of Machine Comprehension Algorithms
B Bingi – 2018 – shodhgangotri.inflibnet.ac.in
… So, the models used bilingual parallel corpora to induce paraphrases based on tech- niques from phrase-based statistical machine translation [16] … Question generation systems can also be deployed as chatbot components (eg, asking questions to start a conversation or to …

A Development of Chatbot Q&A System to Answer Questions in Webpage–Focused on arts education matching services
JM Kim, HM Lee, MY Kim, WH Lee… – ????????? …, 2018 – db.koreascholar.com
… for statistical machine translation”, arXiv preprint arXiv:1406.1078, 2014. Websites 3 “The Complete Beginner’s Guide To Chatbots”,https://chatbotsmagazine.com/the-com plete-beginner-s-guide-to-chatbots-8280b7b906ca 5 Denny Britz, “Deep Learning for Chatbot” …

Activity Recognition: Translation across Sensor Modalities Using Deep Learning
T Okita, S Inoue – Proceedings of the 2018 ACM International Joint …, 2018 – dl.acm.org
… For example, a chatbot is a conversational agent which exchanges words with human being. We develop a chat- bot for telemedicine which identifies the possible diseases for patients[8]. Combined with IoT technology, we want a chatbot to assess the condition of the patient or …

Vol. 2: MT Users’ Track
J Doyon, D Jones – 2018 – aclweb.org
… this year include: automatic conversion of one language variation to another, integration of MT into chatbots, and automatic … Less Post-Editing Bill Lafferty 223 Leveraging Data Resources for Cross-Linguistic Information Retrieval Using Statistical Machine Translation Steve Sloto …

Introduction to the Thematic Section on Computational Linguistics
A Gelbukh – Computación y Sistemas, 2018 – cys.cic.ipn.mx
… In particular, they compare how alternative encoder- decoder deep learning architectures perform in the context of chatbots … Vijay Kumar Sharma and Namita Mittal from India in their paper “An Improvement in Statistical Machine Translation in Perspective of Hindi- English Cross …

Transient Simulation for High-Speed Channels with Recurrent Neural Network
T Nguyen, T Lu, J Sun, Q Le, K We… – 2018 IEEE 27th …, 2018 – ieeexplore.ieee.org
… using recurrent neural network (RNN) in time-series predictions such as language modeling, machine translation, chatbot, and forecasting … H. Schwenk, and Y. Bengio, “Learning phrase representations using RNN encoder- decoder for statistical machine translation,” CoRR, vol …

LSTM Based Self-Defending AI Chatbot Providing Anti-Phishing
SS Kovalluri, A Ashok, H Singanamala – Proceedings of the First …, 2018 – dl.acm.org
… Initially this problem was mapped to statistical machine translation (SMT) problem [42] … After detecting the category, each categorized email is transferred to dedicated chatbot rooms. Each category has specially trained chatbots, and they will reply back to the spammers through …

Arabic Chatbots: A Survey
S AlHumoud, A Al Wazrah… – INTERNATIONAL …, 2018 – researchgate.net
… [10] K. Cho et al., “Learning Phrase Representations using RNN Encoder– Decoder for Statistical Machine Translation,” 2014, pp. 1724–1734. [11] HN Io and CB Lee, “Chatbots and conversational … [12] S. AbdulKader and J. Woods, “Survey on Chatbot Design Techniques …

Improving Computer Generated Dialog with Auxiliary Loss Functions and Custom Evaluation Metrics
T Conley, JS Clair, J Kalita – cs.uccs.edu
… ANN-based Seq2Seq models have been used by many recent chatbots (Vinyals and Le, 2015; Li et al., 2016b,a … Ritter, Cherry, and Dolan (2011) were the first to use a model used for Statistical Machine Translation (SMT) to generate … 1https://github.com/pender/chatbot-rnn …

Intelligent Software Engineering: Synergy between AI and Software
T Xie – pdfs.semanticscholar.org
… Turned into Genocidal Racist (2016 March 23/24) http://www.businessinsider.com/ai-expert- explains-why-microsofts-tay-chatbot-is-so-racist-2016-3 “There are a number of precautionary … Overall better than statistical machine translation • Worse controllability …

Conversation Modeling with Neural Network
JY Patil, GP Potdar – Asian Journal of Research in Computer …, 2018 – journalajrcos.com
… Keywords: Natural language processing; deep learning; Chatbots; natural language understanding; artificial intelligence; neural networks; reinforcement learning. 1 INTRODUCTION … The model proposed leads to improved BLEU score for statistical machine translation …

Chatbot integration within Sitecore Experience Platform
G Albertengo, R Di Vittorio – webthesis.biblio.polito.it
… In the second one is presented the chatbot’s world: starting from the first bot developed until nowa- days, explaining their history, how they … Going on, the next chapter is about the Microsoft Bot Framework, a powerful tools for creating, developing and managing chatbots, with a ii …

Master thesis: Design and implementation of a chatbot in the context of customer support
F Peters – 2018 – matheo.uliege.be
… via text is a computer program or not [1]. However this test’s ambition is much greater than the usual use case of chatbots; the main difference being that the domain knowledge of a chatbot is narrow whereas the Turing test assumes one can talk about any topic with the agent …

NLP-QA Framework Based on LSTM-RNN
X Zhang, MH Chen, Y Qin – 2018 2nd International Conference …, 2018 – ieeexplore.ieee.org
… Question Answering has great commercial value.QA chatbots can answer agent’s question without human help … Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation[J]. Computer Science, 2014 …

Improving Domain Independent Question Parsing with Synthetic Treebanks
HA Boukaram, N Habash, M Ziadee… – Proceedings of the Joint …, 2018 – aclweb.org
… The manual treebank covers two domains: talk shows and chatbots … In our case, using only the synthetic QTemp treebank, we achieved a 32.3% on the Chatbot test set … In Proceedings of the Seventh Workshop on Statistical Machine Translation, pages 422–432 …

Automatic article commenting: the task and dataset
L Qin, L Liu, W Bi, Y Wang, X Liu, Z Hu, H Zhao… – arXiv preprint arXiv …, 2018 – arxiv.org
… making comments thus become a valuable functionality for online forums, intelligent chatbots, etc … on ar- ticles is one of the increasingly demanded skills of intelligent chatbot (Shum et al … In Pro- ceedings of the Third Workshop on Statistical Machine Translation, pages 115–118 …

Intelligence Is Asking The Right Question: A Study On Japanese Question Generation
L Nio, K Murakami – 2018 IEEE Spoken Language Technology …, 2018 – ieeexplore.ieee.org
… is an interesting challenge be- cause its applications involve a vast amount of domains such as a chatbot component in … However, there have also been some reports of traditional statistical machine translation (SMT) approaches that boast better per- formance, especially in …

FaGoN: Fake News Detection model using Grammatic Transformation on Neural Network
Y Seo, CS Jeong – saki.siit.tu.ac.th
… Sequence to sequence learning is mostly used in language model for translation system and chatbot system since the amount of grammar rules are large … [9] P. Langlais, A. Patry and F. Gotti, “A Greedy Decoder for Phrase-Based Statistical Machine Translation”, Conference of …

Stay on-topic: Generating context-specific fake restaurant reviews
M Juuti, B Sun, T Mori, N Asokan – European Symposium on Research in …, 2018 – Springer
… The authors proposed the use of a penalty to commonly occurring sentences (n-grams) in order to emphasize maximum mutual information-based generation. The authors investigated the use of NMT models in chatbot systems …

On Evaluating and Comparing Open Domain Dialog Systems
A Venkatesh, C Khatri, A Ram, F Guo, R Gabriel… – arXiv preprint arXiv …, 2018 – arxiv.org
… However, we do not believe that Turing Test is a suitable mechanism to evaluate chatbots for the following … have been used in both the MT (Gupta et al., 2015; Albrecht and Hwa, 2007) and chatbot domains (Lowe … Findings of the 2011 workshop on statistical machine translation …

Impact of Auxiliary Loss Functions on Dialogue Generation Using Mutual Information
JS Clair, T Conley, J Kalita – cs.uccs.edu
… presented a data- driven approach to generating responses to Twitter status posts, using statistical machine translation, treating a … Seq2Seq models have been used by many re- cent chatbots (Vinyals and Le 2015; Li … The chatbot can thus create a response relevant to the input …

Data Generation Using Sequence-to-Sequence
A Joshi, K Mehta, N Gupta… – 2018 IEEE Recent …, 2018 – ieeexplore.ieee.org
… on the transliteration problem, we presume it can effectively be mapped to other sequence-to-sequence problems, like Q&A, Translation and Conversational Chatbots, as well … Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine …

Dialog generation using multi-turn reasoning neural networks
X Wu, A Martinez, M Klyen – Proceedings of the 2018 Conference of the …, 2018 – aclweb.org
… Dialogue systems such as chatbots are a thriving topic that is attracting increasing attentions … On the other hand, statistical machine translation (SMT) systems have been applied to dialogue systems … a “document”, current user’s query as a “question” and the chatbot’s re- sponse …

A reinforced topic-aware convolutional sequence-to-sequence model for abstractive text summarization
L Wang, J Yao, Y Tao, L Zhong, W Liu, Q Du – arXiv preprint arXiv …, 2018 – arxiv.org
… There- fore, the higher level alignment could be a potential assist. For example, the topic information has been introduced to a RNN-based sequence-to-sequence model [Xing et al., 2017] for chatbots to generate more informative responses …

Effective Character-Augmented Word Embedding for Machine Reading Comprehension
Z Zhang, Y Huang, P Zhu, H Zhao – CCF International Conference on …, 2018 – Springer
… BV, Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., Bengio, Y.: Learning phrase representations using rnn encoder-decoder for statistical machine translation … Zhu, P., Zhang, Z., Li, J., Huang, Y., Zhao, H.: Lingke: A fine-grained multi-turn chatbot for customer service …

An Ensemble of Retrieval-Based and Generation-Based Human-Computer Conversation Systems.
Y Song, R Yan, CT Li, JY Nie, M Zhang, D Zhao – 2018 – openreview.net
… (2013)). Recently, researchers have paid increasing attention to open-domain, chatbot-style human-computer conversations such as XiaoIce1 and Duer2 due to their important commercial values … Statistical Machine Translation …

Topic-Net Conversation Model
M Peng, D Chen, Q Xie, Y Zhang, H Wang… – … Conference on Web …, 2018 – Springer
… In this paper, we study the response generation problem of open-domain chatbots. Notably our goal is to generate responses which are more interesting, diverse and informative … [17] deemed response generation as a statistical machine translation (SMT) problem …

Artificial intelligence in the rising wave of deep learning: The historical path and future outlook [perspectives]
L Deng – IEEE Signal Processing Magazine, 2018 – ieeexplore.ieee.org
… Examples are nar- row-domain dialogue systems and chat- bots, chess-playing programs, traffic light controllers, optimization software for logistics of good deliveries, etc … 2000. [24] F. Och, “Minimum error rate training in statistical machine translation,” in Proc. Assoc …

Applications of Sequence to Sequence Models for Technical Support Automation
G Aalipour, P Kumar, S Aditham… – … Conference on Big …, 2018 – ieeexplore.ieee.org
… two bi-directional LSTM networks we developed to build our chatbot and summarization … would also like to dissect the conversation aspect of chatbots in more … Bengio, “Learning phrase representations using rnn encoder-decoder for statistical machine translation,” arXiv preprint …

Learning to collaborate for question answering and asking
D Tang, N Duan, Z Yan, Z Zhang, Y Sun, S Liu… – Proceedings of the …, 2018 – aclweb.org
… funda- mental QA tasks in research community and of great importance in industrial applications includ- ing web search and chatbot … The features come from a phrase table which is extracted from bilingual corpus via statistical machine translation approach (Koehn et al., 2003) …

Incorporating discriminator in sentence generation: a gibbs sampling method
J Su, J Xu, X Qiu, X Huang – Thirty-Second AAAI Conference on Artificial …, 2018 – aaai.org
… 5502 Page 8. sequence-to-sequence task, chatbot for example. Lastly, we are wondering whether it will be an improvement, to replace a segment in the sentence at a time, in order to gain more flu- ent intermediate sentences …

The First Conversational Intelligence Challenge
M Burtsev, V Logacheva, V Malykh, IV Serban… – The NIPS’17 …, 2018 – Springer
… by user success in the task, in a way that a good chatbot should be … We expect that the next year’s chatbots will be more successful and more interesting to … In Proceedings of the Second Workshop on Statistical Machine Translation, StatMT ’07, pages 228–231, Stroudsburg, PA …

Learning to control the specificity in neural response generation
R Zhang, J Guo, Y Fan, Y Lan, J Xu… – Proceedings of the 56th …, 2018 – aclweb.org
… explore the possibility in de- veloping a general purpose AI system in language (eg, chatbots) … Most methods in this line are constructed within the statistical machine translation (SMT) frame- work, where a … When we apply our model to a chat- bot, there might be different ways to …

Epilogue: Frontiers of NLP in the Deep Learning Era
L Deng, Y Liu – Deep Learning in Natural Language Processing, 2018 – Springer
… learning have been applied to all three types of dialogue systems or chatbots (intelligent assistants … The progress in this research frontier is gaining greater urgency as chatbot conversations are expected to … The mathematics of statistical machine translation: Parameter estimation …

Content-Oriented User Modeling for Personalized Response Ranking in Chatbots
B Liu, Z Xu, C Sun, B Wang, X Wang, DF Wong… – IEEE/ACM Transactions …, 2018 – dl.acm.org
… Besides, Statistical Machine Translation (SMT) based methods are also intuitive for this task; Ritter et al … Being aware of the importance of the leading role of chatbots, Li et al … The personalized chat is a newly emerging demand in the research on chatbot; thus, little work has been …

Emotional Human Machine Conversation Generation Based on SeqGAN
X Sun, X Chen, Z Pei, F Ren – 2018 First Asian Conference on …, 2018 – ieeexplore.ieee.org
… The purpose of our emotional tags is to make the chatbot understood the emotion of the input sequence … D. Bahdanau, F. Bougares, H. Schwenk, and Y. Bengio, “Learning phrase representations using rnn encoder-decoder for statistical machine translation,” arXiv preprint …

EmotionX-Area66: Predicting Emotions in Dialogues using Hierarchical Attention Network with Sequence Labeling
R Saxena, S Bhat, N Pedanekar – … of the Sixth International Workshop on …, 2018 – aclweb.org
… With the advent of social media and dialogue systems like personal assistants and chatbots, Speaker Utterance Emotion Joey Whoa-whoa, Treeger made you cry? surprise … 2014. Learning phrase representations using rnn encoder-decoder for statistical machine translation …

Augmenting Neural Response Generation with Context-Aware Topical Attention
N Dziri, E Kamalloo, KW Mathewson… – arXiv preprint arXiv …, 2018 – arxiv.org
… (Li et al., 2016b) used deep reinforcement learning to generate highly- rewarded responses by considering three dialogue properties: ease of answering, informativeness and coherence. (Zhang et al., 2018) addressed the challenge of personalizing the chatbot by …

Text Data Augmentation Made Simple By Leveraging NLP Cloud APIs
C Coulombe – arXiv preprint arXiv:1812.04718, 2018 – arxiv.org
… That said, it is an open secret that usage of hand-crafted rules which includes noise injection and regular expressions would commonly be used by practioners to augment text data, a bit like hand-crafted rules found in almost all chatbot engines …

Vietnamese Diacritics Restoration Using Deep Learning Approach
BT Hung – 2018 10th International Conference on Knowledge …, 2018 – ieeexplore.ieee.org
… This method considered the accent predicting as statistical machine translation (SMT) problem with source language as accentless texts and … into written Vietnamese texts is important for many applications including question-answering, text extraction, chatbot, search engines …

Different Facets of Text Based Automated Question Answering System
V Singh – researchgate.net
… participation at QA@CLEF 2007, where it is integrated with its statistical Machine Translation engine for … et al., [35] has proposed the design and implementation of a chatbot-based interface … allow a natural discourse to take place by emulating the behaviour of chatbots [42] that …

Response selection from unstructured documents for human-computer conversation systems
Z Yan, N Duan, J Bao, P Chen, M Zhou, Z Li – Knowledge-Based Systems, 2018 – Elsevier
… Side-by-side evaluation between DocChat and a famous chatbot demonstrates that DocChat performs better on domain related queries … 4] train a statistical machine translation (SMT) model using large-scale human-human conversation data and use it as a response generator …

NEXUS Network: Connecting the Preceding and the Following in Dialogue Generation
H Su, X Shen, W Li, D Klakow – arXiv preprint arXiv:1810.00671, 2018 – arxiv.org
… 1 Introduction With the availability of massive online conver- sational data, there has been a surge of in- terest in building open-domain chatbots with data-driven approaches … RL: Deep reinforcement learning chatbot as in (Li et al., 2016c) …

Recurrent convolutional neural network for answer selection in community question answering
X Zhou, B Hu, Q Chen, X Wang – Neurocomputing, 2018 – Elsevier
… Answer selection in CQA is to recognize good or relevant answers for generating useful question–answer (QA) pairs, which are valuable to enrich the knowledge base of many intelligent systems, like automatic question answering [1] or chatbot [2]. Even though some works on …

Hierarchical variational memory network for dialogue generation
H Chen, Z Ren, J Tang, YE Zhao, D Yin – … of the 2018 World Wide Web …, 2018 – dl.acm.org
Page 1. Hierarchical Variational Memory Network for Dialogue Generation Hongshen Chen? Data Science Lab, JD.com chenhongshen@jd.com Zhaochun Ren? Data Science Lab, JD.com renzhaochun@jd.com Jiliang Tang …

NEXUS Network: Connecting the Preceding and the Following in Dialogue Generation
X Shen, H Su, W Li, D Klakow – Proceedings of the 2018 Conference on …, 2018 – aclweb.org
… 1 Introduction With the availability of massive online conver- sational data, there has been a surge of in- terest in building open-domain chatbots with data-driven approaches … RL: Deep reinforcement learning chatbot as in (Li et al., 2016c) …

Countering Language Drift via Grounding
J Lee, K Cho, D Kiela – 2018 – openreview.net
… What had in fact happened was that two chatbots, under certain conditions, had, rather unsurprisingly, started diverging from their English training data and had instead reverted to their own ungrammatical … Moses: Open source toolkit for statistical machine translation …

Generating Classical Chinese Poems via Conditional Variational Autoencoder and Adversarial Training
J Li, Y Song, H Zhang, D Chen, S Shi, D Zhao… – Proceedings of the 2018 …, 2018 – aclweb.org
… Conventionally, rule-based mod- els (Zhou et al., 2010) and statistical machine translation (SMT) models (He et al., 2012) are *Corresponding author: Rui Yan (ruiyan@pku.edu.cn) †Work was partially done at Tencent AI Lab. proposed for this task …

Incorporating Relevant Knowledge in Context Modeling and Response Generation
Y Li, W Li, Z Cao, C Chen – arXiv preprint arXiv:1811.03729, 2018 – arxiv.org
… Dolan 2011) that first formulates the response generation problem as Statistical Machine Translation (SMT), and … In two-party human- computer conversational systems, chatbots interact with users by returning … Hence, chatbot is fed with a sequence of words x = {x1, ··· ,xNx }, and …

MEMD: A Diversity-Promoting Learning Framework for Short-Text Conversation
M Zou, X Li, H Liu, Z Deng – … of the 27th International Conference on …, 2018 – aclweb.org
… 2014. Learning phrase representations using RNN encoder-decoder for statistical machine translation … Yu Wu, Wei Wu, Chen Xing, Ming Zhou, and Zhoujun Li. 2017. Sequential matching network: A new architecture for multi-turn response selection in retrieval-based chatbots …

Paragraph-level Neural Question Generation with Maxout Pointer and Gated Self-attention Networks
Y Zhao, X Ni, Y Ding, Q Ke – Proceedings of the 2018 Conference on …, 2018 – aclweb.org
Page 1. Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 3901–3910 Brussels, Belgium, October 31 – November 4, 2018. c 2018 Association for Computational Linguistics 3901 …

Tailored Sequence to Sequence Models to Different Conversation Scenarios
H Zhang, Y Lan, J Guo, J Xu, X Cheng – … of the 56th Annual Meeting of …, 2018 – aclweb.org
… natural language processing applications such as customer services, intelligent assistant and chat- bot … experiments on the pub- lic Chinese Weibo dataset (social chatbot) show that … framework for dialogue generation is inspired by the studies of statistical machine translation …

Language style transfer
T Shen – 2018 – dspace.mit.edu
… plain/poetic, serious/humorous, democratic/republican, different personal styles, etc. 15 Page 16. It has a wide range of applications, such as to design personalized chatbots, and to appropriately convey a message according to different social contexts. Moreover …

Study and Analysis of various Deep Learning Methodologies for Speech Recognition
SM Joshi, J Umale – ijrpublisher.com
… Speech Recognition based Chatbot’s has become need of now a days applications … Language modeling is also used in many other natural language processing applications such as document classification or statistical machine translation …

Personalized response generation by Dual-learning based domain adaptation
M Yang, W Tu, Q Qu, Z Zhao, X Chen, J Zhu – Neural Networks, 2018 – Elsevier
… in a large variety of applications, such as e-commerce, technical support services, entertaining chatbots, information retrieval … Inspired by recent success of recurrent neural network (RNN) in statistical machine translation, most non-goal-oriented conversational systems employ …

Multitask learning for neural generative question answering
Y Huang, T Zhong – Machine Vision and Applications, 2018 – Springer
… Building chatbot in human–computer conversation via natural language is one of the most challenging … [25] use a phased-based statistical machine translation model to … the topic information into the encoder–decoder framework to generate interesting responses for chatbots …

Investigating Deep Reinforcement Learning Techniques in Personalized Dialogue Generation
M Yang, Q Qu, K Lei, J Zhu, Z Zhao, X Chen… – Proceedings of the 2018 …, 2018 – SIAM
… has become increasingly important in a large variety of applications, ranging from technical support services to entertaining chatbots … Inspired by the recent success of recurrent neural networks (RNN) in statistical machine translation, most non-goal-oriented dialogue systems …

Modeling Non-Goal Oriented Dialog With Discrete Attributes
C Sankar, S Ravi – alborz-geramifard.com
… Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation. ArXiv e-prints, June 2014. [5] J. Chung, C. Gulcehre, K. Cho, and Y. Bengio … A Deep Reinforcement Learning Chatbot. ArXiv e-prints, September 2017 …

Information-Oriented Evaluation Metric for Dialogue Response Generation Systems
P Liu, S Zhong, Z Ming, Y Liu – 2018 IEEE 30th International …, 2018 – ieeexplore.ieee.org
… Ritter et al. [10] used a statistical machine translation (SMT) model to generate dialogue responses, and … B. The Evaluation of Different Models by The Proposed Metric In this section, we use our metric to evaluate three existing Seq2Seq models and two commercial chatbots …

Learning to Coordinate Multiple Reinforcement Learning Agents for Diverse Query Reformulation
R Nogueira, J Bulian, M Ciaramita – arXiv preprint arXiv:1809.10658, 2018 – arxiv.org
… A systematic comparison of smoothing techniques for sentence- level bleu. In Proceedings of the Ninth Workshop on Statistical Machine Translation, pp. 362– 367, 2014 … Learning phrase representations using rnn encoder-decoder for statistical machine translation …

Table-to-text: Describing table region with natural language
J Bao, D Tang, N Duan, Z Yan, Y Lv, M Zhou… – Thirty-Second AAAI …, 2018 – aaai.org
Page 1. Table-to-Text: Describing Table Region with Natural Language Junwei Bao, †? Duyu Tang, ‡ Nan Duan, ‡ Zhao Yan, § Yuanhua Lv, Ming Zhou, ‡ Tiejun Zhao † † Harbin Institute of Technology, Harbin, China ‡ Microsoft Research, Beijing, China …

Dave the debater: a retrieval-based and generative argumentative dialogue agent
DT Le, CT Nguyen, KA Nguyen – Proceedings of the 5th Workshop on …, 2018 – aclweb.org
… 3.1 Format of a debate The aim of the chatbot is to be able to carry a conversation with humans to debate about a given topic. At the initial step, the system suggests a topic (Table 1) and the user can decide to debate on this topic or move on to another one …

MINISTRY OF EDUCATION OF AZERBAIJAN BAKU ENGINEERING UNIVERSITY
MH Ismayil – researchgate.net
… and Stanford started to release large QA datasets. This improvement was revolution- ary, because it did not only improve statistical models for scientific purposes, but also the companies started to implement them inside search engine, chatbots or voice assis- tants. Page 18. 10 …

NIPS Conversational Intelligence Challenge 2017 Winner System: Skill-based Conversational Agent with Supervised Dialog Manager
I Yusupov, Y Kuratov – Proceedings of the 27th International Conference …, 2018 – aclweb.org
… This is not an optimal way of evaluating chatbots either, because a relevant answer can be different from an … In Proceedings of the Second Workshop on Statistical Machine Translation, StatMT ’07, pages 228–231, Stroudsburg, PA, USA … A deep reinforcement learning chatbot …

Image inspired poetry generation in xiaoice
WF Cheng, CC Wu, R Song, J Fu, X Xie… – arXiv preprint arXiv …, 2018 – arxiv.org
… (Yan et al. 2013) formulate the task as an optimization problem based on a generative summarization framework under several constraints. (Jiang and Zhou 2008) present a phrase-based statistical machine translation to generate the second sentence from the first sen …

A Prospective-Performance Network to Alleviate Myopia in Beam Search for Response Generation
Z Wang, Y Bai, B Wu, Z Xu, Z Wang… – Proceedings of the 27th …, 2018 – aclweb.org
… Kyunghyun Cho, Bart van Merrienboer, C¸ aglar Gülçehre, Dzmitry Bahdanau, Fethi Bougares, Holger Schwenk, and Yoshua Bengio. 2014. Learning phrase representations using RNN encoder-decoder for statistical machine translation …

ImprovChat: An AI-enabled Dialogue Assistant Chatbot for English Language Learners (ELL)
Y Guo – 2018 – openresearch.ocadu.ca
… Figure 3.2 Architecture of the web application . . . . . 27 Figure 3.3 Sketches of the chatbot icons … 38 xiii Page 14. xiv Page 15. 1 INTRODUCTION ImprovChat fuses ideas of improvisational theatre with chat, including chat- ting and chatbots …

AirDialogue: An environment for goal-oriented dialogue research
W Wei, Q Le, A Dai, J Li – Proceedings of the 2018 Conference on …, 2018 – aclweb.org
… Talk and Walk (de Vries et al., 2018) 80 2 Dialogue Generation 10,000 Negotiation Chatbot (Lewis et al., 2017) 3 7 × 3 Dialogue Generation Dialogue Self-play 5,808 Frames (El Asri et al., 2017) Unknown 20 Dialogue Generation State Tracking 1,369 …

DLCEncDec: A Fully Character-Level Encoder-Decoder Model for Neural Responding Conversation
S Wu, Y Li, X Zhang, Z Wu – 2018 IEEE 42nd Annual Computer …, 2018 – ieeexplore.ieee.org
… Recent years have witnessed a surge of interest in building conversation systems such as smart agents or chatbots … Bougares, H. Schwenk, and Y. Bengio, “Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation,” empirical methods …

A Bi-Encoder LSTM Model for Learning Unstructured Dialogs
D Shekhar – 2018 – digitalcommons.du.edu
… Abstract Creating a data-driven model that is trained on a large dataset of unstructured dialogs is a crucial step in developing a Retrieval-based Chatbot systems. This thesis presents a Long … 35 2.3 Current State of Research on Chatbot Systems …

Quality Assessment of Conversational Agents: Assessing the Robustness of Conversational Agents to Errors and Lexical Variability
J Guichard – 2018 – diva-portal.org
… In recent years, these agents, also known as chatbots, have become more and more popular … Statistical Machine Translation (SMT) treats translating as a prob- abilistic task, the goal being to find the most likely output se- quence given an input …

Chat Discrimination for Intelligent Conversational Agents with a Hybrid CNN-LMTGRU Network
DS Moirangthem, M Lee – Proceedings of The Third Workshop on …, 2018 – aclweb.org
… Deep learning based models have achieved great success in many NLP tasks, including learn- ing distributed word, sentence and document rep- resentation (Mikolov et al., 2013; Le and Mikolov, 2014), parsing (Socher et al., 2013), statistical machine translation (Cho et al …

Improving Response Selection in Multi-turn Dialogue Systems
D Chaudhuri, A Kristiadi, J Lehmann… – arXiv preprint arXiv …, 2018 – arxiv.org
… 2014). 2.1 Generative models Ritteretal. (2011) were the first to formu- late the task of automatic response generation as phrase-based statistical machine translation, which they tackled with n-gram-based language models. Later …

Customized nonlinear bandits for online response selection in neural conversation models
B Liu, T Yu, I Lane, OJ Mengshoel – Thirty-Second AAAI Conference on …, 2018 – aaai.org
… Introduction Conversational agents, or chatbots, have a wide range of applications such as in technical support, personalized ser- vice, and entertainment (Young et al … Ritter et al. (2011) framed conversation response generation as a statistical machine translation problem …

Why You Should Listen to This Song: Reason Generation for Explainable Recommendation
G Zhao, H Fu, R Song, T Sakai, X Xie… – 2018 IEEE International …, 2018 – ieeexplore.ieee.org
… Furthermore, we deploy our proposed methods on XiaoIce chatbot, and observe that the click-through rate of recommended songs improves by at least 8.2% over four different … Learn- ing phrase representations using RNN encoder-decoder for statistical machine translation …

COBOTS-A Cognitive Multi-Bot Conversational Framework for Technical Support
S Subramaniam, P Aggarwal, GB Dasgupta… – Proceedings of the 17th …, 2018 – dl.acm.org
… Service is a cloud-based dialog management service for creating chat bots using IBM … Azure SREBot: More than a Chatbot {\textemdash} an Intelligent Bot to Crush Mitigation Time … Applications of Statistical Machine Translation Approaches to Spoken Language Understanding …

The Impact of Conversational Agents on Humans in Services: Research Questions and Hypotheses
C B?lan – Bucharest 2018, 2018 – mbd.ase.ro
… approached the open domain response generation by means of phrase-based statistical machine translation (Ritter et al … of humans to different types of interfaces used when they interact with a chatbot. Two types of chatbots were used, respectively a simple text chatbot and a …

Rich short text conversation using semantic-key-controlled sequence generation
K Yu, Z Zhao, X Wu, H Lin, X Liu – IEEE/ACM Transactions on Audio …, 2018 – dl.acm.org
… It is also observed that by manu- ally manipulating the memory trigger, it is possible to interpretably guide the topics or semantics of the reply. Index Terms—Question and answer, chatbot, short text conversation (STC), sequence to sequence learning. I. INTRODUCTION …

Conversational query understanding using sequence to sequence modeling
G Ren, X Ni, M Malik, Q Ke – Proceedings of the 2018 World Wide Web …, 2018 – dl.acm.org
… com ABSTRACT Understanding conversations is crucial to enabling conversational search in technologies such as chatbots, digital assistants, and smart home devices that are becoming increasingly popular. Conventional …

Translating Natural Language Sentences into Database Query
E Varsha, PC Rafeeque – 2018 International Conference on …, 2018 – ieeexplore.ieee.org
… It can be used for Natural language search, Intelligent chat-bots, Question- Answering etc … Bahdanau, Fethi Bougares, Holger Schwenk, and Yoshua Bengio,(2014), ”Learning phrase representations using RNN encoder-decoder for statistical machine translation”, arXiv preprint …

Where Corpus Linguistics and Artificial Intelligence (AI) Meet
M Pace-Sigge – Spreading Activation, Lexical Priming and the …, 2018 – Springer
This chapter will provide a platform to showcase the more recent developments that have grown out of the early laid groundwork. The latest theories in the field of linguistics will be presented,…

Analyzing and Predicting Emoji Usages in Social Media
P Zhao, J Jia, Y An, J Liang, L Xie, J Luo – Companion of the The Web …, 2018 – dl.acm.org
Page 1. Analyzing and Predicting Emoji Usages in Social Media Peijun Zhao zhaopeijun0328@163.com Department of Computer Science and Technology, Tsinghua University Key Laboratory of Pervasive Computing, Ministry …

The Natural Auditor: How To Tell If Someone Used Your Words To Train Their Model
C Song, V Shmatikov – arXiv preprint arXiv:1811.00513, 2018 – arxiv.org
… Text-generation models for tasks such as next-word prediction (the basis of query autocompletion and predictive virtual keyboards) and di- alog generation (the basis of chatbots and automated customer service) are extensively trained on sensitive personal data, including users …

Natural Language Processing with Java: Techniques for building machine learning and neural network models for NLP
RM Reese, AS Bhatia – 2018 – books.google.com
… a Chatbot Chatbot architecture Artificial Linguistic Internet Computer Entity Understanding AIML Developing a chatbot using ALICE … You’ll learn about statistical machine translation, summarization, dialog systems, complex searches, supervised and unsupervised NLP, and other …

A Question Type Driven Framework to Diversify Visual Question Generation.
Z Fan, Z Wei, P Li, Y Lan, X Huang – IJCAI, 2018 – ijcai.org
… skill of asking is important in a variety of ar- eas, eg, providing demonstrations in child education [Ku- nichika et al., 2004], initializing a conversation for chat- bots [Mostafazadeh et al … Learning phrase representations using rnn encoder-decoder for statistical machine translation …

Neural Response Ranking for Social Conversation: A Data-Efficient Approach
I Shalyminov, O Dušek, O Lemon – arXiv preprint arXiv:1811.00967, 2018 – arxiv.org
… Prize challenge made it possi- ble to collect large numbers of dialogues between real users of Amazon Echo devices and various chatbots … Learning phrase representations using rnn encoder–decoder for statistical machine translation … A deep reinforcement learning chatbot …

Using Deep Learning and an External Knowledge Base to Develop Human-Robot Dialogues
JY Huang, TA Lin, WP Lee – 2018 IEEE International …, 2018 – ieeexplore.ieee.org
… Recently, the demand on chatbots has begun to perform open-domain conversations … 2042-2050. [10] K. Cho, B. Merrienboer, C. Gulcehre, F. Bougares, et al., “Learning Phrase Representations Using RNN encoder-decoder for statistical machine translation,” arXiv preprint …

An overview of computational approaches for analyzing interpretation
P Blandfort, J Hees, DU Patton – arXiv preprint arXiv:1811.04028, 2018 – arxiv.org
… Second, AI approaches have become much more ubiquitous. This is especially prevalent online, where chatbots take part in discussions, recommendation algorithms suggest things we are likely to favor, and search results are nicely ranked by yet another computer model …

Lawyer’s Intellectual Tool for Analysis of Legal Documents in Russian
A Khasianov, I Alimova, A Marchenko… – … and Innovations (IC …, 2018 – ieeexplore.ieee.org
… In the future, we plan to develop chatbot and mobile application for more convenient provision of information … D. Bahdanau, F. Bougares, H. Schwenk, and Y. Bengio, “Learning phrase representations using rnn encoder-decoder for statistical machine translation,” arXiv preprint …

Chat More: Deepening and Widening the Chatting Topic via A Deep Model.
W Wang, M Huang, XS Xu, F Shen, L Nie – SIGIR, 2018 – coai.cs.tsinghua.edu.cn
… select deeper keywords. quality of the repository. The latter generation-based systems, inspired by statistical machine translation, model the mapping between a post and its response with data-driven methods. In the beginning …

Curriculum Learning for Natural Answer Generation.
C Liu, S He, K Liu, J Zhao – IJCAI, 2018 – ijcai.org
… 2 Background 2.1 Task Description Natural Answer Generation can be regarded as a fusion task of knowledge base question answering (KBQA) and chatbot / (one-turn) dialog … Learning phrase representations using rnn encoder–decoder for statistical machine translation …

First Workshop on Advanced Virtual Environments and Education (WAVE2 2018)
AS Gomes, F Moreira, FK de Oliveira – 2018 – researchgate.net
… on the information contained in the Scopus database, a portion of the research involving the theme Chatbots. 4 … Extracting Chatbot Knowledge from Online Discussion Forums … Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation …

Supervised Transfer Learning for Product Information Question Answering
T Lai, T Bui, N Lipka, S Li – 2018 17th IEEE International …, 2018 – ieeexplore.ieee.org
… C. Customer Service Chatbots Developing customer service chatbots for ecommerce web- sites is … SuperAgent introduced in [19] is a powerful chatbot designed to improve … Learning phrase representations using rnn encoder-decoder for statistical machine translation,” in EMNLP …

Web forum retrieval and text analytics: A survey
D Hoogeveen, L Wang, T Baldwin… – … and Trends® in …, 2018 – nowpublishers.com
Page 1. Preprint Foundations and Trends R in Information Retrieval Vol. 12, No. 1 (2018) 1–163 c 2018 D. Hoogeveen, L. Wang, T. Baldwin, KM Verspoor DOI: 10.1561/1500000062 Web Forum Retrieval and Text Analytics: a Survey …

Autonomy and Privacy with Open Federated Virtual Assistants
MS Lam – nlp.stanford.edu
Page 1. Autonomy and Privacy with Open Federated Virtual Assistants Monica S. Lam Computer Science Department Stanford University 1 Page 2. Summary: Autonomy and Privacy with Open Federated Virtual Assistants Large …

Unfolding Recurrent Neural Networks
P Goyal, S Pandey, K Jain – Deep Learning for Natural Language …, 2018 – Springer
… The same model could be used for chatbots, language translation, and other related purposes … was proposed by Yoshua Bengio and others in the research paper “Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation” ( https://arxiv …

Unsupervised Stylish Image Description Generation via Domain Layer Norm
CK Chen, ZF Pan, M Sun, MY Liu – arXiv preprint arXiv:1809.06214, 2018 – aaai.org
… Ideally, a stylish IDG model should allow users to flexibly control over the generated de- scriptions as shown in Fig 1. Such a model would be useful for increasing user engagement in applications requiring hu- man interaction such as chatbot and social media sharing …

A Knowledge-Grounded Multimodal Search-Based Conversational Agent
S Agarwal, O Dusek, I Konstas, V Rieser – arXiv preprint arXiv:1810.11954, 2018 – arxiv.org
… Conversational agents have become ubiquitous, with variants ranging from open-domain conversa- tional chit-chat bots (Ram et al., 2018; Papaioan- nou et al., 2017; Fang et al., 2017) to domain- specific task-based dialogue systems (Singh et al., 2000; Rieser and Lemon …

Dialog-to-Action: Conversational Question Answering Over a Large-Scale Knowledge Base
D Guo, D Tang, N Duan, M Zhou, J Yin – Advances in Neural …, 2018 – papers.nips.cc
Paper accepted and presented at the Neural Information Processing Systems Conference (http://nips.cc/).

Curriculum Learning for Natural Answer Generation
S He, C Liu, K Liu, J Zhao – 2018 – ir.ia.ac.cn
… 2 Background 2.1 Task Description Natural Answer Generation can be regarded as a fusion task of knowledge base question answering (KBQA) and chatbot / (one-turn) dialog … Learning phrase representations using rnn encoder–decoder for statistical machine translation …

An Affect-Rich Neural Conversational Model with Biased Attention and Weighted Cross-Entropy Loss
P Zhong, D Wang, C Miao – arXiv preprint arXiv:1811.07078, 2018 – arxiv.org
… For real-world appli- cations, Fitzpatrick, Darcy, and Vierhile (2017) developed a rule-based empathic chatbot to deliver cognitive behavior therapy to young adults with depression and anxiety, and ob- tained significant results on depression reduction …

Review of State-of-the-Art in Deep Learning Artificial Intelligence
VV Shakirov, KP Solovyeva… – Optical Memory and …, 2018 – Springer
… When neural chat bots are trained to produce words with low perplexity in relation to the train- ing corpus of texts, they become capable to write coherent stories, to answer intelligibly, with common sense, to questions, related to the recently loaded information, to reason in a …

DialogWAE: Multimodal response generation with conditional wasserstein auto-encoder
X Gu, K Cho, J Ha, S Kim – arXiv preprint arXiv:1805.12352, 2018 – arxiv.org
… Kyunghyun Cho, Bart Van Merriënboer, C¸ alar Gülçehre, Dzmitry Bahdanau, Fethi Bougares, Hol- ger Schwenk, and Yoshua Bengio. Learning phrase representations using RNN Encoder–Decoder for statistical machine translation … Modeling situations in neural chat bots …

iBot: An Agent-based Software Framework For Creating Domain Conversational Agents
PE Velmovitsky – 2018 – maxwell.vrac.puc-rio.br
… Other modern chatbots use Statistical Machine Translation techniques to “translate” input into output responses … This allows chatbots developers to have great efficacy and efficiency in developing and deploying intelligent chatbot applications for specific domains and …

Coupled context modeling for deep chit-chat: towards conversations between human and computer
R Yan, D Zhao – Proceedings of the 24th ACM SIGKDD International …, 2018 – dl.acm.org
… most hardcore problems in computer science. Conversational systems are of growing importance due to their promising potentials and com- mercial values as virtual assistants and chatbots. To build such systems with adequate …

A survey of available corpora for building data-driven dialogue systems: The journal version
IV Serban, R Lowe, P Henderson… – Dialogue & …, 2018 – dad.uni-bielefeld.de
… Hybrid or combined models, such as the model built on both a phrase-based statistical machine translation system and a recurrent neural network proposed by Sordoni et al … Their model uses a statistical machine translation model to map a dialogue history to its response …

Deep neural networks based on gating mechanism for open-domain question answering
CA Mayhua Tijera – 2018 – repositorio.ucsp.edu.pe
… ELIZA was able to talk about any topic by using very simple rules that detected important words in the input. It was a very rudimentary model to answer questions, but it generated a series of chatbots that participated in the annual Loebner Prize1 …

Hacia un diccionario global
E Iklódi – 2018 – riunet.upv.es
… An early version of conversational agents and certain strongly domain-based chatbots are already out on the market, providing 24 hour, immediate assistance for customers … chatbots and by other NLP tasks which in the strict sense of the word are not considered semantic …

Deep Context Resolution
J Chen – 2018 – uwspace.uwaterloo.ca
… iii Page 4. Abstract Conversations depend on information from the context. To go beyond one-round con- versation, a chatbot must resolve contextual information such as: 1) co-reference resolution, 2) ellipsis resolution, and 3) conjunctive relationship resolution …

Between the Lines: Machine Learning for Prediction of Psychological Traits-A Survey
D Johannßen, C Biemann – … Domain Conference for Machine Learning and …, 2018 – Springer
… Koko 6 is an anonymous emotional peer-to-peer support network, used by Kshirsagar et al. [12]. The dataset originated from a clinical study at the MIT and can be implemented as chatbot service. It offers 106,000 labeled posts, with and some without crisis …

Text-Driven Head Motion Synthesis Using Neural Networks
BTS Bojlén – btao.org
… mapping (as noted in Yehia et al. [7]). However, a ”ground truth” speech signal from which to generate motion is not always available, for example in conversational chatbots or digital assistants. In these cases, one option is to …

Creating an Emotion Responsive Dialogue System
A Vadehra – 2018 – uwspace.uwaterloo.ca
… Chapter 1 Introduction Dialogue systems, conversational agents and chatbots are a well researched area in NLP. There has been a plethora of research trying to create domain/task specific and domain agnostic chatbots … Rule based systems were some of the initial chatbots …

Evorus: A Crowd-powered Conversational Assistant Built to Automate Itself Over Time
THK Huang, JC Chang, JP Bigham – … of the 2018 CHI Conference on …, 2018 – dl.acm.org
… [35] generated responses based on phrase-based statistical machine translation based on … PART I: LEARNING TO CHOOSE CHATBOTS OVER TIME Evorus’ chatbot selector learns over time … Ranking and Sampling Chatbots Upon receiving a message from a user, Evorus uses …

KITE: Building conversational bots from mobile apps
TJJ Li, O Riva – Proceedings of the 16th Annual International …, 2018 – dl.acm.org
… 1 INTRODUCTION The promise and excitement around conversational chatbots, or sim- ply bots, has rapidly grown in … This approach has shown promise for non task-oriented “chit-chat” bots [11, 65, 79], where the … Task models of this type encapsulate the logic behind a chatbot …

Measuring Short Text Semantic Similarity with Deep Learning Models
J Ge – 2018 – yorkspace.library.yorku.ca
Page 1. Measuring Short Text Semantic Similarity with Deep Learning Models Jun Ge A THESIS SUBMITTED TO THE FACULTY OF GRADUATE STUDIES IN PARTIAL FULFILMENT OF THE REQUIREMENTS FOR THE DEGREE OF MASTER OF ARTS …

Design of an Intelligent Agent for Stimulating Brainstorming
CH Wang, TY Li – Proceedings of the 2018 10th International …, 2018 – dl.acm.org
… 2. RELATED WORKS In previous years, chatbots established on instant messaging software or web-based Q&A systems … 5]. Regarding dialogue generation, one research based on information retrieval and phrase-based statistical machine translation techniques presented …

Response Generation For An Open-Ended Conversational Agent
N Dziri – 2018 – era.library.ualberta.ca
… 25 2.4.1 Chatbot systems … 3, 6, 20, 22–24, 28–33, 47, 49, 50, 56, 60, 63, 64 SMT Statistical Machine Translation. 28 … fluent and engaging responses. Nowadays, chatbots are gaining popularity worldwide and big companies are increasingly investing millions of dollars to 1 …

Style Transfer and Extraction for the Handwritten Letters Using Deep Learning
O Mohammed, G Bailly, D Pellier – arXiv preprint arXiv:1812.07103, 2018 – arxiv.org
… One aspect of a successful human-machine interface (eg human-robot interaction, chatbots, speech, handwriting …) is the … F. Bougares, H. Schwenk, and Y. Bengio, “Learning phrase representations using rnn encoder-decoder for statistical machine translation,” arXiv preprint …

Natural Language Processing with TensorFlow: Teach language to machines using Python’s deep learning library
T Ganegedara – 2018 – books.google.com
… translation 312 A brief historical tour of machine translation 313 Rule-based translation 313 Statistical Machine Translation (SMT) 315 … and target sentences 361 Other applications of Seq2Seq models – chatbots 363 Training a chatbot 364 Evaluating chatbots – Turing test …

Improving retrieval modeling using cross convolution networks and multi frequency word embedding
G An, M Shafiee, D Shamsi – arXiv preprint arXiv:1802.05373, 2018 – arxiv.org
… edu davood.shamsi@oath.com Abstract To build a satisfying chatbot that has the abil- ity of managing a goal-oriented multi-turn di- alogue, accurate modeling of human conver- sation is crucial. In this paper we concen- trate …

Modeling multi-turn conversation with deep utterance aggregation
Z Zhang, J Li, P Zhu, H Zhao, G Liu – arXiv preprint arXiv:1806.09102, 2018 – arxiv.org
… translation. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP 2014), pages 1724–1734. Lei Cui, Shaohan Huang, Furu Wei, Chuanqi Tan, Chaoqun Duan, and Ming Zhou. 2017. Superagent: A customer service chatbot for e …

Conversational memory network for emotion recognition in dyadic dialogue videos
D Hazarika, S Poria, A Zadeh, E Cambria… – Proceedings of the …, 2018 – aclweb.org
… Emo- tion detection from such resources can benefit numerous fields like counseling (De Choudhury et al., 2013), public opinion mining (Cambria et al., 2017), financial forecasting (Xing et al., 2018), and intelligent systems such as smart homes and chat- bots (Young et al …

Analysis, discovery and exploitation of open data for the creation of question-answering systems
G Molina Gallego – 2018 – rua.ua.es
… Chatbots have been become more popular from the last two decades, actually, many companies use these systems to have feedback about their products or services or launch a new publicity campaign. To better understand the potential of a chatbot, it is needed to know their …

Improving Dialog Systems Using Knowledge Graph Embeddings
B Carignan – 2018 – curve.carleton.ca
… SMT Statistical Machine Translation WMT Workshop on Statistical Machine Translation xii Page 13 … CHAPTER 2. BACKGROUND 6 2.1.2 Early Chatbots ELIZA [11] is an early chatbot program which uses a series of scripts to process user inputs and output pre-set responses …

Temporality-enhanced knowledgememory network for factoid question answering
X Duan, S Tang, S Zhang, Y Zhang, Z Zhao… – Frontiers of Information …, 2018 – Springer
Page 1. 104 Duan et al. / Front Inform Technol Electron Eng 2018 19(1):104-115 Frontiers of Information Technology & Electronic Engineering www.jzus.zju.edu.cn; engineering.cae.cn; www.springerlink.com ISSN 2095-9184 …

Towards Understanding Code-Mixed Telugu-English Data
DS Jitta – 2018 – web2py.iiit.ac.in
Page 1. Towards Understanding Code-Mixed Telugu-English Data Thesis submitted in partial fulfillment of the requirements for the degree of MS in Computational Linguistics by Research by Divya Sai Jitta 201225167 jittadivya.sai@research.iiit.ac.in …

A Neural Generation-based Conversation Model Using Fine-grained Emotion-guide Attention
Z Zhou, M Lan, Y Wu – 2018 International Joint Conference on …, 2018 – ieeexplore.ieee.org
… commonsense knowledge,” in AAAI, 2018. [2] Y. Wu, W. Wu, C. Xing, C. Xu, Z. Li, and M. Zhou, “A sequential matching framework for multi-turn response selection in retrieval-based chatbots,” in ACL, 2017. [3] I. Sutskever, O. Vinyals …

Response Selection and Automatic Message-Response Expansion in Retrieval-Based QA Systems using Semantic Dependency Pair Model
MH Su, CH Wu, KY Huang, WH Lin – ACM Transactions on Asian and …, 2018 – dl.acm.org
… driven approaches [25–26], such as generation-based methods that employed statistical machine translation techniques to … between the post and the response [8]. The retrieval-based chatbots choose a … A QA system that serves as a chatbot for emotional support and comforting …

The RLLChatbot: a solution to the ConvAI challenge
N Gontier, K Sinha, P Henderson, I Serban… – arXiv preprint arXiv …, 2018 – arxiv.org
… Furthermore, since Alexa is a voice-activated assistant, the chatbot relies on the accuracy of the speech recognizer provided. Many chatbots have been proposed for this challenge, overall they all rely on modern deep learning and reinforcement learning techniques and try to …

Hands-On Natural Language Processing with Python: A practical guide to applying deep learning architectures to your NLP applications
R Arumugam, R Shanmugamani – 2018 – books.google.com
… Summary Chapter The Question-Answering 9: Question-Answering task and Chatbots Using Memory … the chatbot on the testing set Interacting with the chatbot Putting it … Using the Attention-Based Model Overview of machine translation Statistical machine translation English …

Dialog manager for conversational AI
BP Marek – 2018 – core.ac.uk
… 57 C Alquist Conversational Dataset examples 59 Page 17. Chapter 1 Introduction Personal voice assistants and text chatbots are newly emerging types of user interface. Their increasing popularity drives the need for better dialogue managers. This need will be accel …

Dialogový manažer pro konverza?ní um?lou inteligenci
P Marek – 2018 – dspace.cvut.cz
… 57 C Alquist Conversational Dataset examples 59 Page 17. Chapter 1 Introduction Personal voice assistants and text chatbots are newly emerging types of user interface. Their increasing popularity drives the need for better dialogue managers. This need will be accel …

Automatic Comprehension of Customer Queries for Feedback Generation
NE Okwunma – 2018 – wiredspace.wits.ac.za
… Service (CNS) was used as test case. A prototype chat-bot application was developed that takes customer queries in a chat, automatically maps them to a FAQ, and presents … prototype chat-bot application was developed. This chat-bot takes customer queries in …

The First Financial Narrative Processing Workshop (FNP 2018)
M El-Haj, P Rayson, A Moore – 2018 – lrec-conf.org
… Proposed framework is used in our in-house German language banking and finance chatbots. General challenges of German language processing and finance-banking domain chatbot language models and lexicons are also introduced …

Michael Pace-Sigge
L PRIMING – Springer
Page 1. SPREADING ACTIVATION, LEXICAL PRIMING AND THE SEMANTIC WEB Michael Pace-Sigge Early Psycholinguistic Theories, Corpus Linguistics and AI Applications Page 2. Spreading Activation, Lexical Priming and the Semantic Web Page 3. Michael Pace-Sigge …

Find the Conversation Killers: A Predictive Study of Thread-ending Posts
Y Jiao, C Li, F Wu, Q Mei – Proceedings of the 2018 World Wide Web …, 2018 – dl.acm.org
… proposed model. For the widely concerned topic, our analysis also offers implications for how to improve the quality and user experience of online conversations, or how to engage users in a conversation with a chatbot. KEYWORDS …

Spreading Activation, Lexical Priming and the Semantic Web: Early Psycholinguistic Theories, Corpus Linguistics and AI Applications
M Pace-Sigge – 2018 – books.google.com
Page 1. SPREADING ACTIVATION, LEXICAL PRIMING AND THE SEMANTIC WEB Early Psycholinguistic Theories, Linguistics Corpus and AI Applications Michael Pace-Sigge Page 2. Spreading Activation, Lexical Priming and the Semantic Web Page 3 …

Context-Aware Dialog Re-Ranking for Task-Oriented Dialog Systems
J Ohmura, M Eskenazi – 2018 IEEE Spoken Language …, 2018 – ieeexplore.ieee.org
… Li, “Sequential matching network: A new architecture for multi-turn response selection in retrieval-based chat- bots,” in Proceedings of … Schwenk, and Yoshua Bengio, “Learning phrase rep- resentations using rnn encoder-decoder for statistical machine translation,” arXiv preprint …

A Face-to-Face Neural Conversation Model
H Chu, D Li, S Fidler – … of the IEEE Conference on Computer …, 2018 – openaccess.thecvf.com
… In [20], the authors formulated the prob- lem as statistical machine translation, where the goal was to “translate” the query posts in blogs into a response … 5.2. The NeuralHank Chatbot Here, we test how our model’s performance in the eyes of real human users …

AI4D: Artificial Intelligence for Development
S Mann, M Hilbert – Available at SSRN 3197383, 2018 – papers.ssrn.com
Page 1. Electronic copy available at: https://ssrn.com/abstract=3197383 Artificial Intelligence for Development: AI4D Martin Hilbert & Supreet Mann University of California, Davis, March 20, 2018 (hilbert@ucdavis.edu) ARTIFICIAL INTELLIGENCE: THE THEORY 3 …

To copy or not to copy? Text-to-text neural question generation
T Hosking – 2018 – tomho.sk
Page 1. To copy or not to copy? Text-to-text neural question generation Tom Hosking Project Supervisor Prof Sebastian Riedel Industry Partner Dr Guillaume Bouchard, Bloomsbury AI http://bloomsbury.ai Department of Computer Science University College London (UCL) …

A Rule of Persons, Not Machines: The Limits of Legal Automation
FA Pasquale – Not Machines: The Limits of Legal Automation …, 2018 – papers.ssrn.com
… computerized interactions with customers, and chatbots like DoNotPay guide users through challenges to parking tickets … Obtaining a fishing license with a chatbot makes sense—and we should see more and better examples of such “civic tech” in coming years.22 On the other …

Natural Language Processing and Chinese Computing: 7th CCF International Conference, NLPCC 2018, Hohhot, China, August 26–30, 2018, Proceedings
M Zhang, V Ng, D Zhao, S Li, H Zan – 2018 – books.google.com
Page 1. Min Zhang· Vincent Ng· Dongyan Zhao Sujian Li· Hongying Zan (Eds.) Natural Language Processing and Chinese Computing 7th CCF International Conference, NLPCC 2018 Hohhot, China, August 26–30, 2018 Proceedings, Part I 123 Page 2 …

Neural Networks for Language Modeling and Related Tasks in Low-Resourced Domains and Languages
O TILK – 2018 – digi.lib.ttu.ee
… Survival of small languages largely depends on their utility in modern use cases like voice interfaces for computer systems, automatic transcription, chatbots, automatic translation and summarization, predictive keyboards, optical character recognition and handwritten text …

Neural networks for sentiment analysis in AsterixDB
JMK Finckenhagen – 2018 – brage.bibsys.no
… Self-driving cars, intelligent personal assistants like Siri and Alexa and chatbots are all over the news. NNs plays an important role in many of these concepts, and makes an effort to create an abstraction of how we believe the human brain makes decisions …

Deep Semantic Learning for Conversational Agents
M Morisio, M Mensio – 2018 – webthesis.biblio.polito.it
… The spreading of these agents, also called bots or chatbots, has highlighted an important need: going beyond the simple (often pre-computed) answer and provide personalized answers according to users’ profiles … 12 2 State of the Art 13 2.1 Chatbots and their classification …

Neural Creative Language Generation
M Ghazvininejad – 2018 – search.proquest.com
… business data (Anand and Kahn, 1992). The widespread use of the Internet intro- duced new NLG applications. Generating canned responses, customer service chat … Page 16. bots, and conversation agents like Siri and Cortana are a few examples. Mean …

Analysing Seq-to-seq Models in Goal-oriented Dialogue: Generalising to Disfluencies.
S Bouwmeester – 2018 – esc.fnwi.uva.nl
… Dialogue systems are used in a wide range of applications, such as technical support services, digital personal assistants, chat bots, and home … A marked example of this is Microsoft’s AI-based chat-bot named Tay, who was terminated after it became racist due to bad input from …

Finding Good Representations of Emotions for Text Classification
JH Park – arXiv preprint arXiv:1808.07235, 2018 – arxiv.org
… a friend and making a conversation. When training NLP models, such as chatbots, things do not always go as intended. Famous incident of Microsoft chatbot Tay, which learned directly from users’ tweets with- out any filtering …

Predictive Market Capitalization by Topic Analysis forClients’ Engagement in Financial Industries
J Santhappan – 2018 – search.proquest.com
Page 1. PREDICTIVE MARKET CAPITALIZATION BY TOPIC ANALYSIS FOR CLIENTS’ ENGAGEMENT IN FINANCIAL INDUSTRIES A Dissertation Presented in Partial Fulfillment of the Requirements for the Degree of Doctor of Computer Science By Jayasri Santhappan …

Towards Deep Conversational Recommendations
R Li, SE Kahou, H Schulz, V Michalski… – Advances in Neural …, 2018 – papers.nips.cc
… They use this data to develop a chat bot … We aim at developing an agent capable of chatting with a partner and asking questions about their movie tastes in order to make movie recommendations. One might therefore characterize our system as a recommendation “chat-bot” …

TwitSong: A current events computer poet and the thorny problem of assessment.
C Lamb – 2018 – uwspace.uwaterloo.ca
Page 1. TwitSong: A current events computer poet and the thorny problem of assessment. by Carolyn Elizabeth Lamb A thesis presented to the University of Waterloo in fulfillment of the thesis requirement for the degree of Doctor of Philosophy in Computer Science …

Examining Personality Differences in Chit-Chat Sequence to Sequence Conversational Agents
X Yujie – 2018 – eprints.illc.uva.nl
… Examples for task-oriented CA are chat- bots for booking restaurants or flights, where a conversation is closed once the agent has finished the task … (2011), where the response generation task for CA was treated as a statistical machine translation task …

Discovering Gated Recurrent Neural Network Architectures
A Mok, K Holekamp – 2018 – nn.cs.utexas.edu
… The inflow and outflow of information to and from these cells is controlled by associated input/output gated units. Such LSTM based memory networks are also used to build chat-bots, speech recognition and forecasting systems. The time-series prediction problem in such …

4REAL 2018 Workshop on Replicability and Reproducibility of Research Results in Science and Technology of Language
A Branco, N Calzolari, K Choukri – 2018 – lrec-conf.org
Page 1. LREC 2018 Workshop 4REAL 2018 Workshop on Replicability and Reproducibility of Research Results in Science and Technology of Language PROCEEDINGS Edited by António Branco, Nicoletta Calzolari and Khalid Choukri ISBN: 979-10-95546-21-4 …