Text Classification & Dialog Systems 2017


Notes:

In general, automatic text classification plays a vital role in text summarization, question answering and information extraction.  Automatic text classification is usually done by using a prelabeled training set and applying various machine learning methods such as naive Bayes, support vector machines, artificial neural networks, or hybrid approaches that combine various machine learning methods to improve the efficiency of classification.

  • Automatic text classification
  • Term selection
  • Text categorization
  • Text classifier

Resources:

Wikipedia:

References:

See also:

100 Best GitHub: Text Segmentation | NPCEditor | Stanford ClassifierStatistical Classification & Dialog Systems


Variational Autoencoder for Semi-Supervised Text Classification.
W Xu, H Sun, C Deng, Y Tan – AAAI, 2017 – aaai.org
Page 1. Variational Autoencoder for Semi-Supervised Text Classification … Abstract Although semi-supervised variational autoencoder (SemiVAE) works in image classification task, it fails in text classification task if using vanilla LSTM as its decoder …

Spoken language understanding for a nutrition dialogue system
M Korpusik, J Glass – IEEE/ACM Transactions on Audio …, 2017 – ieeexplore.ieee.org
… KORPUSIK AND GLASS: SPOKEN LANGUAGE UNDERSTANDING FOR A NUTRITION DIALOGUE SYSTEM … Recent work has shown sig- nificant performance improvement over previous state-of-the art text classification techniques using very deep character-level CNNs [63] …

Convolutional neural networks for multi-topic dialog state tracking
H Shi, T Ushio, M Endo, K Yamagami… – Dialogues with Social …, 2017 – Springer
… in the ‘INFO’ slot, and the average number of dialog segments related to each value is around 15, which we considered as insufficient compared to other typical text classification task such … 1. Lemon, O., Pietquin, O.: Data-Driven Methods for Adaptive Spoken Dialogue Systems …

Learning utterance-level representations for speech emotion and age/gender recognition using deep neural networks
ZQ Wang, I Tashev – Acoustics, Speech and Signal Processing …, 2017 – ieeexplore.ieee.org
… To our best knowledge, this is the first attempt to perform emotion detection for Mandarin in a spoken dialogue system … 74–99, 2015. [3] A. Joulin, E. Grave, P. Bojanowski, and T. Mikolov, ?Bag of Tricks for Efficient Text Classification,? in arXiv preprint arXiv: 1607.01759, 2016 …

Deconvolutional paragraph representation learning
Y Zhang, D Shen, G Wang, Z Gan… – Advances in Neural …, 2017 – papers.nips.cc
… Quantitative evaluation on semi-supervised text classification and summarization tasks demonstrate the potential for better utilization of long unlabeled text data … toward more applied tasks, such as sentiment analysis [1, 2, 3, 4], machine translation [5, 6, 7], dialogue systems [8 …

A Unified Model for Cross-Domain and Semi-Supervised Named Entity Recognition in Chinese Social Media.
H He, X Sun – AAAI, 2017 – aaai.org
… Bhatt, HS; Semwal, D.; and Roy, S. 2015. An iterative similarity based adaptation technique for cross domain text classification. CoNLL 2015 52. Bhatt, HS; Sinha, M.; and Roy, S. 2016. Cross-domain text classification with multiple domains and disparate label sets …

SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient.
L Yu, W Zhang, J Wang, Y Yu – AAAI, 2017 – aaai.org
Page 1. SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient Lantao Yu, † Weinan Zhang, †? Jun Wang, ‡ Yong Yu † † Shanghai Jiao Tong University, ‡ University College London {yulantao,wnzhang,yyu}@apex.sjtu.edu.cn, j.wang@cs.ucl.ac.uk Abstract …

Using acoustic paralinguistic information to assess the interaction quality in speech-based systems for elderly users
H Pérez-Espinosa, J Martínez-Miranda… – International Journal of …, 2017 – Elsevier
… Georgila et al. (2008) created a corpus of interactions made by older and young users using a Wizard-of-Oz (WoZ)-based dialogue system, where they designed and annotated this corpus to examine the impact of cognitive aging on user interactions with this type of system …

Adversarial ranking for language generation
K Lin, D Li, X He, M Sun, Z Zhang – Advances in Neural Information …, 2017 – papers.nips.cc
… language processing, which is essential to many applications such as machine translation [1], image captioning [6], and dialogue systems [26] … show that the convolutional neural network can achieve high performance for machine translation [7, 34] and text classification [36] …

Just ASK: Building an Architecture for Extensible Self-Service Spoken Language Understanding
A Kumar, A Gupta, J Chan, S Tucker… – arXiv preprint arXiv …, 2017 – arxiv.org
… Iulian V Serban, Alessandro Sordoni, Yoshua Bengio, Aaron Courville, and Joelle Pineau, “Building end-to-end dialogue systems using generative … [36] Armand Joulin, Edouard Grave, and Piotr Bojanowski Tomas Mikolov, “Bag of tricks for efficient text classification,” EACL 2017 …

A roadmap for natural language processing research in information systems
D Liu, Y Li, MA Thomas – … of the 50th …, 2017 – hl-128-171-57-22.library.manoa …
… the refinement and application of NLP techniques to solve real-world problems [3], such as creating spoken dialogue systems [4], speech … of NLP-related tasks, based on a thorough review of literature, we synthesize 12 prototypical NLP tasks: text classification or categorization …

Conversational bootstrapping and other tricks of a concierge robot
S Guo, J Lenchner, J Connell, M Dholakia… – Proceedings of the 2017 …, 2017 – dl.acm.org
… 34] humanoid robots Pepper and NAO, and the telepresence robot known as Double from Double Robotics[4]. Keywords Spoken dialog systems; text classification; online learning; conversational agents; human-robot interaction; concierge robots 1. INTRODUCTION A number …

Chat Detection in an Intelligent Assistant: Combining Task-oriented and Non-task-oriented Spoken Dialogue Systems
S Akasaki, N Kaji – arXiv preprint arXiv:1705.00746, 2017 – arxiv.org
… Although it lies outside the scope of this paper to explore how to exploit chat detection method in a full dialogue system, the chat … The second classifier uses a convolutional neu- ral network (CNN) because it has recently proven to perform well on text classification problems (Kim …

Unsupervised text classification for natural language interactive narratives
J Bellassai, AS Gordon… – Proceedings of the …, 2017 – pdfs.semanticscholar.org
… Related Work Natural language processing in interactive narratives has his- torically shared many of the methods and technologies of research in natural language dialogue systems … Supervised text classification was used in the TLAC- XL (Hill et al …

Sarcasm detection in microblogs using Naïve Bayes and fuzzy clustering
S Mukherjee, PK Bala – Technology in Society, 2017 – Elsevier
… the difficulties, the huge benefit of detecting sarcasm has been recognized in many computer interaction based applications, such as, review summarization, dialogue systems and review … We have shown how the Naïve Bayes classifier works in the case of text classification …

Explanation and justification in machine learning: A survey
O Biran, C Cotton – IJCAI-17 Workshop on Explainable AI (XAI), 2017 – intelligentrobots.org
… explanation sufficient for tasks such as picking the next course in a college curriculum;[Dodson et al., 2011] propose a dialog system, instead of a … predict the model’s success with new samples.[Lei et al., 2016] select small snippets of the input text of text classification tasks as …

Natural language processing
K Sirts – 2017 – courses.cs.ut.ee
… POS tagging • Morphology • Syntactic parsing • Lexical semantics • Information extraction • Text classification • Sentiment analysis • Information retrieval • Machine translation • Natural language generation • Text summarization • Dialog systems 23 Page 24. The general plan …

Learning to generate one-sentence biographies from Wikidata
A Chisholm, W Radford, B Hachey – arXiv preprint arXiv:1702.06235, 2017 – arxiv.org
… Recent work explores unsupervised autoencoding objectives in sequence-to-sequence models, im- proving both text classification as a pretraining step (Dai and Le, 2015) and translation as a multi- task objective (Luong et al., 2016) …

Zero-shot learning across heterogeneous overlapping domains
A Kumar, PR Muddireddy, M Dreyer… – Proc. Interspeech, 2017 – isca-speech.org
… Natural Language Understanding (NLU) in many commercial spoken dialog systems uses a simplified shallow semantic pars- ing formalism which attempts to classify each utterance into an output class representing the intended action of a user, known as an Intent, while …

Short answers to deep questions: supporting teachers in large?class settings
J McDonald, RJ Bird, A Zouaq… – Journal of Computer …, 2017 – Wiley Online Library
… Appendix 1. Student written (typed) responses were captured by a surface-based natural language tutorial dialogue system developed by the first author and described elsewhere (McDonald, Knott, Stein & Zeng, 2013). The …

Identifying latent beliefs in customer complaints to trigger epistemic rules for relevant human-bot dialog
C Anantaram, A Sangroya – Control, Automation and Robotics …, 2017 – ieeexplore.ieee.org
… Figure 1: System architecture of car diagnosis dialog system carried out and the next set of beliefs are then asserted … Categorization gives us the broad direction of the main problem faced by the customer. Text classification is a foundational task in many NLP applications …

Opinion Mining and Sentiment Analysis
E Breck, C Cardie – The Oxford Handbook of Computational …, 2017 – oxfordhandbooks.com
Opinions are ubiquitous in text, and readers of online text—from consumers to sports fans to news addicts to governments—can benefit from automatic methods that synthesize useful opinion-oriented information from the sea of data. In this chapter on opinion mining and sentiment …

Convolutional Neural Network using a threshold predictor for multi-label speech act classification
G Xu, H Lee, MW Koo, J Seo – Big Data and Smart Computing …, 2017 – ieeexplore.ieee.org
… 1-13. [7] J. Nam, J. Kim, EL Mencía, I. Gurevych, and J. Furnkranz, “Large- scale multi-label text classification – Revisiting Neural … submission to the DSTC 4 Spoken Language Understanding pilot task,” In 7th International Workshop on Spoken Dialogue Systems (IWSDS), 2016 …

A Comparative Study of Text Preprocessing Techniques for Natural Language Call Routing
R Sergienko, M Shan, A Schmitt – Dialogues with Social Robots, 2017 – Springer
… Topic categorization of user utterances can be also useful for multi-domain spoken dialogue system design [2]. In this work we treat call routing as an example of a natural language understanding application based on text classification …

Comparative Analysis of Word Embedding Methods for DSTC6 End-to-End Conversation Modeling Track
Z Bairong, W Wenbo, L Zhiyu… – … 6th Dialog System …, 2017 – workshop.colips.org
… [6] A. Joulin, E. Grave, P. Bojanowski, and T. Mikolov, “Bag of tricks for efficient text classification,” arXiv preprint … Hakkani-Tur, P. Pasupat, and R. Sarikaya, “Enriching word embeddings using knowledge graph for semantic tagging in conversational dialog systems,” genre, 2010 …

Dialogue Act Sequence Labeling using Hierarchical encoder with CRF
H Kumar, A Agarwal, R Dasgupta, S Joshi… – arXiv preprint arXiv …, 2017 – arxiv.org
… 2014) is in building a natural language dialogue system, where knowing the DAs of the past utterances helps in the prediction of the DA of the current utterance, and thus, limiting the number of candidate utterances to be generated for the current turn …

A Simple and Effective Lagrangian-Based Combinatorial Algorithm for S $ $^ 3$ $3 VMs
F Bagattini, P Cappanera, F Schoen – International Workshop on Machine …, 2017 – Springer
… Joachims, T.: Transductive inference for text classification using support vector machines … Li, B., Yang, Z., Zhu, Y., Meng, H., Levow, G., King, I.: Predicting user evaluations of spoken dialog systems using semi-supervised learning …

Natural language inference over interaction space
Y Gong, H Luo, J Zhang – arXiv preprint arXiv:1709.04348, 2017 – arxiv.org
… learning techniques, attention mechanism is broadly applied in many NLU tasks since its introduction: machine translation(Bahdanau et al., 2014), abstractive summa- rization(Rush et al., 2015), Reading Comprehension(Hermann et al., 2015), dialog system(Mei et al., 2016 …

Robust Task Clustering for Deep Many-Task Learning
M Yu, X Guo, J Yi, S Chang, S Potdar… – arXiv preprint arXiv …, 2017 – arxiv.org
… Data We test our methods by conducting experiments on three text classification datasets … 2. Diverse Real-World Tasks: User Intent Classification for Dialog System The second dataset is from an on-line service which trains and serves intent classification models to various clients …

Topic Identification for Speech without ASR
C Liu, J Trmal, M Wiesner, C Harman… – arXiv preprint arXiv …, 2017 – arxiv.org
… in spoken dialogue systems.” in Proc. INTERSPEECH, 2015. [15] Y. Kim, “Convolutional neural networks for sentence classifica- tion,” arXiv preprint arXiv:1408.5882, 2014. [16] X. Zhang, J. Zhao, and Y. LeCun, “Character-level convolutional networks for text classification,” in …

The use of autoencoders for discovering patient phenotypes
H Suresh, P Szolovits, M Ghassemi – arXiv preprint arXiv:1703.07004, 2017 – arxiv.org
… state-of-the-art results in many different natural language processing applications from machine translation [11] to dialogue systems [12] to … They were recently used as an initialization step for recurrent neural networks for text classification [14], but have not been applied to the …

Semantic mapping of natural language input to database entries via convolutional neural networks
M Korpusik, Z Collins, J Glass – Acoustics, Speech and Signal …, 2017 – ieeexplore.ieee.org
… [5] M. Korpusik and J. Glass, “Spoken language understanding in a nutrition dialogue system,” ASLP, Submitted … [16] X. Zhang, J. Zhao, and Y. LeCun, “Character-level convolu- tional networks for text classification,” in Proc. NIPS, 2015, pp. 649–657 …

Annotation and Detection of Emotion in Text-based Dialogue Systems with CNN
J Zhao, Q Gao – arXiv preprint arXiv:1710.00987, 2017 – arxiv.org
… With UTF-8, EmoNet gains the ability to perform in multi-language dialogue systems … [13] Hao L, Hao L. Automatic identification of stop words in Chinese text classification[C]//Computer Science and Software Engineer- ing, 2008 International Conference on …

User Intention Classification in an Entities Missed In-vehicle Dialog System
K Zhang, Q Zhu, N Zhang, Z Shi, Y Zhan – International Conference in …, 2017 – Springer
… classification method which based on words. DBN achieved good results in the long text classification, however, dialogue systems are often dozens of phrase or word level of intention judgment. Therefore, we need to find a …

A practical approach to dialogue response generation in closed domains
Y Lu, P Keung, S Zhang, J Sun, V Bhardwaj – arXiv preprint arXiv …, 2017 – arxiv.org
… In dialogue systems, Vinyals et al [1] and Serban et al [2] demonstrated that encoder-decoder networks with LSTM units can generate dialogue based on IT help desk and movie script corpuses … Presently, LSTM-based classifiers are standard baselines for text classification tasks …

Text-based Speaker Identification on Multiparty Dialogues Using Multi-document Convolutional Neural Networks
K Ma, C Xiao, JD Choi – Proceedings of ACL 2017, Student Research …, 2017 – aclweb.org
… 2016. Sequen- tial Short-Text Classification with Recurrent and Convolutional Neural Networks … 2015. The Ubuntu Dialogue Corpus: A Large Dataset for Research in Unstructured Multi- Turn Dialogue Systems. In Proceedings of the SIG- DIAL Conference …

Are You Addressing Me? Multimodal Addressee Detection in Human-Human-Computer Conversations
O Akhtiamov, D Ubskii, E Feldina, A Pugachev… – … Conference on Speech …, 2017 – Springer
… Proceedings of ICSLP, vol. 1, pp. 138–141 (2000)Google Scholar. 4. Akhtiamov, O., Sergienko, R., Minker, W.: An approach to Off-Talk detection based on text classification within an automatic spoken dialogue system. In: Proceedings of ICINCO, Lisbon, Portugal, vol. 2, pp …

Lessons in Dialogue System Deployment
A Leuski, R Artstein – Proceedings of the 18th Annual SIGdial Meeting on …, 2017 – aclweb.org
… We analyze deployment of an interactive dialogue system in an environment where deep technical expertise might not be read- ily available … For example, we re-implemented the NPCEditor text classification and dialogue man- agement algorithms as a C++ library, and the im …

Convolutional Neural Network using a threshold predictor for multi-domain dialogue.
G Xu, H Lee – uni-leipzig.de
… 1-13. [7] J. Nam, J. Kim, EL Mencía, I. Gurevych, and J. Furnkranz, “Large- scale multi-label text classification – Revisiting Neural … submission to the DSTC 4 Spoken Language Understanding pilot task,” In 7th International Workshop on Spoken Dialogue Systems (IWSDS), 2016 …

A “small-data”-driven approach to dialogue systems for natural language human computer interaction
T Boros, SD Dumitrescu – Speech Technology and Human …, 2017 – ieeexplore.ieee.org
… 113–124. [5] JD Williams and S. Young, “Partially observable markov decision processes for spoken dialog systems,” Computer Speech & Language, vol … 69–78. [10] S. Lai, L. Xu, K. Liu, and J. Zhao, “Recurrent convolutional neural networks for text classification.” in AAAI, vol …

Text, Speech, and Dialogue: 20th International Conference, Tsd 2017, Prague, Czech Republic, August 27-31, 2017, Proceedings
K Ekštein, V Matoušek – 2017 – books.google.com
… One of the ambitions of the conference is, as its name suggests, not only to deal with dialogue systems but also to improve dialogue among researchers in areas of NLP, ie, among the “text” and … 353 Zden?k Hanzlí?ek Temporal Feature Space for Text Classification …

Deep Learning for Acoustic Addressee Detection in Spoken Dialogue Systems
A Pugachev, O Akhtiamov, A Karpov… – Conference on Artificial …, 2017 – Springer
… dialogue systems (SDSs). Handling this kind of interaction, the system is supposed to distinguish the speech addressed to it (On-talk) from the speech addressed to another human (Off-talk). There are a lot of approaches to solving this problem such as text classification for …

Intension Classification of User Queries in Intelligent Customer Service System
S Song, H Chen, Z Shi – researchgate.net
… of sentences is effective for sentence similarity calculation, and further for the use of document ranking and text classification, etc., in … intention classification in QA system can also be taken as Dialogue Intention Recognition (DIR) [5], and in dialogue systems, understanding user …

Speech recognition in a dialog system: from conventional to deep processing
A Becerra, JI de la Rosa, E González – Multimedia Tools and Applications, 2017 – Springer
… Keywords Speech recognition · Neural networks · Gaussian mixture models · Hidden Markov models · Deep learning · Spoken dialog system … classification), radar processing, speech recognition (including speaker identification and verification), and text classification [6, 21] …

Speech and Text Analysis for Multimodal Addressee Detection in Human-Human-Computer Interaction
O Akhtiamov, M Sidorov, A Karpov… – Proc. Interspeech …, 2017 – isca-speech.org
… syntactical analysis, which may theoretically be applied in different domains. Index Terms: Off-Talk, speaking style, acoustical analysis, syntactical analysis, lexical analysis, text classification, spoken dialogue system 1. Introduction …

Sequential short-text classification with neural networks
F Dernoncourt – 2017 – dspace.mit.edu
Page 1. Sequential Short-Text Classification MAOT ITUTEl OF TECHNQLOGY with Neural Networks JUN 23 201 by Franck Dernoncourt ARCHiVES … Page 3. 2 Page 4. Sequential Short-Text Classification with Neural Networks by Franck Dernoncourt …

Classification-based spoken text selection for LVCSR language modeling
V Chunwijitra, C Wutiwiwatchai – EURASIP …, 2017 – asmp-eurasipjournals.springeropen …
… Classification-based spoken text selection for LVCSR language modeling. Vataya Chunwijitra 1 Email author and; Chai Wutiwiwatchai 1. EURASIP Journal on Audio, Speech, and Music Processing20172017:24 … 4.4 Stylistic text classification methods …

Using Context Information for Dialog Act Classification in DNN Framework
Y Liu, K Han, Z Tan, Y Lei – Proceedings of the 2017 Conference on …, 2017 – aclweb.org
… man conversations, as well as for developing intel- ligent human-to-computer dialog systems (either written or spoken dialogs) … Most of the parameters were chosen based on literature or our experience with other DNN-based text classification tasks …

Emotion Detection from Text via Ensemble Classification Using Word Embeddings
J Herzig, M Shmueli-Scheuer… – Proceedings of the ACM …, 2017 – dl.acm.org
… Forgues [10] used pre-trained word vectors and a linear classi er to classify user intents in dialog systems, however their task and methodology is di erent than ours … 2014. Bootstrapping Dialog Systems with Word Embeddings. (2014). [11] Yoav Goldberg. 2017 …

Dialogue Modelling in Multi-party Social Media Conversation
S Dutta, D Das – International Conference on Text, Speech, and …, 2017 – Springer
… 3.5 Frequency Weight Measures for Common Terms. For text classification techniques, counting tf-idf for words is a vividly used approach … In: van Kuppevelt, JCJ, Dybkær, L., Bernsen, NO (eds.) Advances in Natural Multimodal Dialogue Systems, pp. 23–54 …

Joint Learning of Dialog Act Segmentation and Recognition in Spoken Dialog Using Neural Networks
T Zhao, T Kawahara – Proceedings of the Eighth International Joint …, 2017 – aclweb.org
… systems. Natural language understanding (NLU), as an important component of dialog system, is usually responsible for dialog act (DA) or dialog intent tagging, where text classification techniques are necessary. Dialog act …

Knowledge Guided Short-Text Classification for Healthcare Applications
S Cao, B Qian, C Yin, X Li, J Wei… – Data Mining (ICDM) …, 2017 – ieeexplore.ieee.org
… 1 shows, the chatbot faces a big challenge to determine the user’s intent in a typical dialog system if the utterance contains unrecognized entity … that what contributes to classification is not the shallow entity words, but types the entities belong to in most text classification task …

Dialogue Act Semantic Representation and Classification Using Recurrent Neural Networks
P Papalampidi, E Iosif, A Potamianos – SEMDIAL 2017 SaarDial, 2017 – academia.edu
… 1 Introduction Dialogue Act (DA) classification constitutes a ma- jor processing step in Spoken Dialogue Systems (SDS) assisting the understanding of user input … 2016. Se- quential short-text classification with recurrent and convolutional neural networks …

Combining speech-based and linguistic classifiers to recognize emotion in user spoken utterances
D Griol, JM Molina, Z Callejas – Neurocomputing, 2017 – Elsevier
… Although emotion is receiving increasing attention from the dialog systems community, most research described in the literature is devoted exclusively to … the other hand, machine-learning approaches use algorithms to solve the sentiment analysis as a text classification problem …

Turn-taking Estimation Model Based on Joint Embedding of Lexical and Prosodic Contents
C Liu, C Ishi, H Ishiguro – Proc. Interspeech 2017, 2017 – pdfs.semanticscholar.org
… [13] Raux, A. and Eskenazi, M. (2009). A Finite-State Turn-Taking Model for Spoken Dialog Systems. In Proc. NAACL 2009, Stroudsburg, PA, USA … 2014. [16] A. Joulin, E. Grave, P. Bojanowski, T. Mikolov, (2016). ”Bag of Tricks for Efficient Text Classification” …

Zara Returns: Improved Personality Induction and Adaptation by an Empathetic Virtual Agent
FB Siddique, O Kampman, Y Yang, A Dey… – Proceedings of ACL 2017 …, 2017 – aclweb.org
… This speeds up the compu- tation, which is essential for dialog systems. Raw audio is inserted straight into a CNN … CNNs have also gained popularity recently in ef- ficiently carrying out the task of text classification (Kalchbrenner et al., 2014; Kim, 2014) …

Dialogue Breakdown Detection Considering Annotation Biases
J Takayama, E Nomoto, Y Arase – workshop.colips.org
… As chat-oriented dialogue systems, which are known as chat- bots, implemented by generation-based and example-based ap- proaches gain popularity … Some recent studies have ap- plied the attention mechanism to CNN for text classification [9] and relation extraction [10] …

Rasa: Open Source Language Understanding and Dialogue Management
T Bocklisch, J Faulker, N Pawlowski… – arXiv preprint arXiv …, 2017 – arxiv.org
… [5] A. Joulin, E. Grave, P. Bojanowski, and T. Mikolov. Bag of tricks for efficient text classification. arXiv preprint arXiv:1607.01759, 2016 … [7] P. Lison and C. Kennington. Opendial: A toolkit for developing spoken dialogue systems with probabilistic rules. ACL 2016, page 67, 2016 …

Neural-based Context Representation Learning for Dialog Act Classification
D Ortega, NT Vu – arXiv preprint arXiv:1708.02561, 2017 – arxiv.org
… Automatic DA classification is an impor- tant pre-processing step in natural language under- standing tasks and spoken dialog systems … 2016. Sequen- tial short-text classification with recurrent and con- volutional neural networks. CoRR abs/1603.03827 …

Skill-based Conversational Agent
I Yusupov, Y Kuratov – researchgate.net
… “Neural Question Generation from Text: A Prelim- inary Study.” arXiv preprint arXiv:1704.01792 (2017). [7] Joulin, Armand, et al. “Bag of tricks for efficient text classification.” arXiv preprint arXiv:1607.01759 (2016). [8] DSTC6 – Dialog System Technology Challenges 6 …

A Complete Bibliography of ACM Transactions on Speech and Language Processing (TSLP)
NHF Beebe – 2017 – tug.ctan.org
… Higashinaka:2004:EDU [HMNA04] Ryuichiro Higashinaka, Noboru Miyazaki, Mikio Nakano, and Kiyoaki Aikawa. Evaluating dis- course understanding in spoken dialogue systems. ACM Trans- actions on Speech and Language Processing (TSLP), 1(1):1–20, November 2004 …

Tag Me a Label with Multi-arm: Active Learning for Telugu Sentiment Analysis
SS Mukku, SR Oota, R Mamidi – … Conference on Big Data Analytics and …, 2017 – Springer
… 13. Sravanthi, MC, Prathyusha, K., Mamidi, R.: A Dialogue System for Telugu, a Resource-Poor Language, pp. 364–374 (2015)Google Scholar. 14 … Tong, S., Koller, D.: Support vector machine active learning with applications to text classification. J. Mach. Learn. Res …

Non-Contextual Modeling of Sarcasm using a Neural Network Benchmark
V Ashokkumar, ND Radpour – 2017 – ttic.edu
… One of the most crucial components of natural human-robot interaction is artificial intuition and its influence on dialog systems … Review text classification has progressed from sentiment analysis research in areas not only in sarcasm, but in detec- tion of irony (Reyes, Rosso, and …

Predicting Users’ Negative Feedbacks in Multi-Turn Human-Computer Dialogues
X Wang, J Wang, Y Liu, X Wang, Z Wang… – Proceedings of the Eighth …, 2017 – aclweb.org
… wangbaoxun}@trio.ai Abstract User experience is essential for human- computer dialogue systems. However, it is impractical to ask users to provide explicit feedbacks when the agents’ responses dis- please them. Therefore, in …

Dialogue Act Recognition via CRF-Attentive Structured Network
Z Chen, R Yang, Z Zhao, D Cai, X He – arXiv preprint arXiv:1711.05568, 2017 – arxiv.org
… task. Many applications have benefited from the use of automatic dialogue act recognition such as dialogue systems, machine transla- tion, automatic speech recognition, topic identification and talking avatars [21] [24] [14]. One …

Reconstruct & Crush Network
E Merdivan, MR Loghmani, M Geist – Advances in Neural …, 2017 – papers.nips.cc
… We plan to study further this aspect in the near future, in order to provide an alternative metric for dialogue systems evaluation. Acknowledgments … [6] F. Geli and L. Bing. Social media text classification under negative covariate shift. EMNLP, 2015. [7] WH Greene …

A Study on Natural Language Processing for Human Computer Interaction
N MPSTME – ijarcet.org
… classification problems … Classification of Human Machine Dialog can be done as follows: 1) Finite state based systems 2) Frame based systems 3) Agent based systems [31] 4) Answering systems 5) Semi-dialogue systems 6) Full dialogue systems [32] …

Efficiently Trainable Text-to-Speech System Based on Deep Convolutional Networks with Guided Attention
H Tachibana, K Uenoyama, S Aihara – arXiv preprint arXiv:1710.08969, 2017 – arxiv.org
… Deep Learning Workshop, ICML, 2015. [20] IV Serban et al., “Building end-to-end dialogue systems us- ing generative hierarchical neural network models.,” in Proc. AAAI, 2016, pp … [23] X. Zhang et al., “Character-level convolutional networks for text classification,” in Proc …

Proceedings of the 21st Conference on Computational Natural Language Learning (CoNLL 2017)
R Levy, L Specia – Proceedings of the 21st Conference on …, 2017 – aclweb.org
… 153 xi Page 12. Feature Selection as Causal Inference: Experiments with Text Classification Michael J. Paul … 432 Natural Language Generation for Spoken Dialogue System using RNN Encoder-Decoder Networks Van-Khanh Tran and Le-Minh Nguyen …

Modeling Situations in Neural Chat Bots
S Sato, N Yoshinaga, M Toyoda… – Proceedings of ACL 2017 …, 2017 – aclweb.org
… if the friend is driving a car with you, you might answer “If you fall asleep, we’ll die.” Modeling situations behind conversations has been an open problem in chat dialogue modeling, and this difficulty has partly forced us to focus on task-oriented dialogue systems (Williams and …

Anjishnu Kumar Amazon. com anjikum@ amazon. com
S Tucker, B Hoffmeister, M Dreyer, S Peshterliev… – alborz-geramifard.com
… Iulian V Serban, Alessandro Sordoni, Yoshua Bengio, Aaron Courville, and Joelle Pineau, “Building end-to-end dialogue systems using generative … [47] Armand Joulin, Edouard Grave, and Piotr Bojanowski Tomas Mikolov, “Bag of tricks for efficient text classification,” EACL 2017 …

Building Generalize QA System, SLR
M Zoaib, H Raza, H Shabbir, M Suleman, HA Asghar – researchgate.net
… blocks. Moreover, it includes text classification, information extraction and summarization techniques … policy. A. Agarwal [80] and Zhang [96] uses text classification, machine learning, support vector machine and kernel method. Fig …

A Chatbot by Combining Finite State Machine, Information Retrieval, and Bot-Initiative Strategy
S Yi, K Jung – sanghyunyi.ml
… [6] Antoine Raux and Maxine Eskenazi. A finite-state turn-taking model for spoken dialog systems … Character-level convolutional networks for text classification. In Advances in neural information processing systems, pages 649–657, 2015 …

Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
G Kondrak, T Watanabe – Proceedings of the Eighth International Joint …, 2017 – aclweb.org
… 536 Combining Lightly-Supervised Text Classification Models for Accurate Contextual Advertising Yiping Jin, Dittaya Wanvarie and Phu Le … 723 End-to-End Task-Completion Neural Dialogue Systems Xiujun Li, Yun-Nung Chen, Lihong Li, Jianfeng Gao and Asli Celikyilmaz …

Breaking the internet barrier
M Li, X Zhu – 2017 – idl-bnc-idrc.dspacedirect.org
… Context-aware Natural Language Generation for Spoken Dialogue Systems. COLING 2016, Osaka, Japan … 8. Li Zhao, Minlie Huang, et al. Semi-Supervised Multinomial Naive Bayes for Text Classification by Leveraging Word-Level Statistical Constraint …

An Architecture Combining Convolutional Neural Network (CNN) and Support Vector Machine (SVM) for Image Classification
AF Agarap – arXiv preprint arXiv:1712.03541, 2017 – arxiv.org
… These include, but are not limited to, image classification[9], natural language processing[12], speech recognition[4], and text classification[14] … 2015. Semantically conditioned lstm-based natural language generation for spoken dialogue systems …

Bilingual Word Embeddings for Cross-Lingual Personality Recognition Using Convolutional Neural Nets
FB Siddique, P Fung – Learning, 2017 – pdfs.semanticscholar.org
… Having such a personality recognition module in dialogue systems will enable us to have more intelligent and personal human-agent conversations in the … local features [20], and such a model is used on top of the learned word embeddings to solve text classification tasks [21 …

Automatic classification of doctor-patient questions for a virtual patient record query task
LC Llanos, S Rosset, P Zweigenbaum – BioNLP 2017, 2017 – aclweb.org
… 3 Task description We classify questions into those that a rule-based dialogue system can process, and those needing a supplementary method … The purpose of collecting the corpus is to train health dialogue systems aimed at simulating a con- sultation with virtual patients …

Conversational Topic Modelling in First Encounter Dialogues
TN Trong, K Jokinen – mmsym.org
… Conventional topic modelling and text classification have mainly focused on static documents, ie documents collected from archives, journals, logs, on-line … 27 64 language technology at the university 64 200 specializing fields in LT 200 278 spoken dialogue systems 278 328 …

UAM’s participation at CLEF eRisk 2017 task: Towards modelling depressed bloggers
E Villatoro-Tello, G Ram?rez-de-la-Rosa… – pdfs.semanticscholar.org
… Even though this type of representation has been evaluated on thematic text classification, our main goal was to determine its pertinence on … Callejas-Rodr?guez, E. Villatoro-Tello, I. Meza, and G. Ram?rez-de-la Rosa, From Dialogue Corpora to Dialogue Systems: Generating a …

Building an Intelligent Call Distributor
TK Tran, DM Pham, B Van Huynh – Computer Science On-line Conference, 2017 – Springer
… From the 1960s to the 1970s, research was carried out into spoken dialog systems such as ELIZA … 97%. 95%. 4 Text Processing. Text classification is the process of assigning a natural language document into one or more given categories automatically …

On the Identification of Suggestion Intents from Vietnamese Conversational Texts
TL Ngo, KL Pham, H Takeda, SB Pham… – Proceedings of the Eighth …, 2017 – dl.acm.org
… role”. We can understand that a turn is a talking section in spoken dialog systems, a post/comment in forums, a twice/status in social media networks … model. It is a flexible technique widely used for a variety of text classification task …

Parallel Hierarchical Attention Networks with Shared Memory Reader for Multi-Stream Conversational Document Classification
N Sawada, R Masumura… – Proc. Interspeech …, 2017 – pdfs.semanticscholar.org
Page 1. Parallel Hierarchical Attention Networks with Shared Memory Reader for Multi-Stream Conversational Document Classification Naoki Sawada1,2, Ryo Masumura1, Hiromitsu Nishizaki3 1NTT Media Intelligence Laboratories …

The commercial NLP landscape in 2017
R Dale – Natural Language Engineering, 2017 – cambridge.org
… of these chatbots are conceptually similar to the much older category of telephony-based spoken language dialogue systems that let … not all of these are provided by every vendor in the space, are named entity recognition, concept extraction, text classification, sentiment analysis …

Subjective Text Mining for Arabic Social Media
NFB Hathlian, AM Hafez – … Journal on Semantic Web and Information …, 2017 – igi-global.com
… An Arabic Stemming Approach using Machine Learning with Arabic Dialogue System. Proceedings of the ICGST AIML ’11Conference. Dubai: UAE. Ikonomakis, M., Kotsiantis, S., & Tampakas, V. (2005, August). Text Classification Using Machine Learning Techniques …

Non-Contextual Modeling of Sarcasm using a Neural Network Benchmark
ND Radpour, V Ashokkumar – arXiv preprint arXiv:1711.07404, 2017 – arxiv.org
… that we present to capture different forms of nuances in communication and making for much more natural and engaging dialogue systems … Review text classification has progressed from sentiment analysis research in areas not only in sarcasm, but in detection of irony (Reyes …

Adapting a Virtual Agent to User Personality
O Kampman, FB Siddique, Y Yang, P Fung – 2017 – uni-ulm.de
… without the need for complex feature extraction upfront, such as in [9]. This speeds up the computation, which is essential for dialog systems … CNNs have gained popularity recently by efficiently carrying out the task of text classification [4], [6]. In particular using pre-trained word …

ML-Ask: Open Source Affect Analysis Software for Textual Input in Japanese
M Ptaszynski, P Dybala… – Journal of …, 2017 – openresearchsoftware.metajnl.com
… states expressed by the user were also used as information on how the user feels about the dialog system they interact … be useful in determining distinguishable features for other tasks related to affect and sentiment analysis, or even generally perceived binary text classification …

Investigating neural architectures for short answer scoring
B Riordan, A Horbach, A Cahill, T Zesch… – Proceedings of the 12th …, 2017 – aclweb.org
… Challenge” (Dzikovska et al., 2013). It consists of two subsets: Beetle, with student responses from interacting with a tutorial dialogue system, and SciEntsBank (SEB) with science assessment questions. We use two label sets …

Text Generation Based on Generative Adversarial Nets with Latent Variable
H Wang, Z Qin, T Wan – arXiv preprint arXiv:1712.00170, 2017 – arxiv.org
… It is also essential to machine translation, text summarization, question answering and dialogue system [1]. One popular ap- proach for text … choose convolutional neural network as the discriminative model, which has shown a great success in the task of text classification [5] [6] …

Feature Selection for Natural Language Call Routing Based on Self-Adaptive Genetic Algorithm
A Koromyslova, M Semenkina… – IOP Conference Series …, 2017 – iopscience.iop.org
… for further routing. Topic categorization of users utterances can be also useful for multidomain spoken dialogue system design [12]. In this work we treat call routing as an example of a text classification application. In the vector …

Read It Aloud to Me
S Celaschi, MS Castro, SP da Cunha – International Conference on …, 2017 – Springer
… The text classification is a binary output in which an input text image is considered readable or non-readable without any character … Nowadays, such tools are employed in real-world applications, creating spoken dialogue systems and speech-to-speech translation engines …

Speech Emotion Recognition based on Gaussian Mixture Models and Deep Neural Networks
IJ Tashev, ZQ Wang, K Godin – Information Theory and …, 2017 – ieeexplore.ieee.org
… EXPERIMENTAL SETUP We have collected 17, 408 real-traffic Mandarin utter- ances from a Microsoft spoken dialogue system … 74–99, 2015. [2] A. Joulin, E. Grave, P. Bojanowski, and T. Mikolov, “Bag of tricks for efficient text classification,” in arXiv preprint arXiv: 1607.01759 …

Question answering system based on sentence similarity
M Kashif, C Arora – 2017 – repository.iiitd.edu.in
… 3.1 Introduction Sentence Similarity measures are widely used in text-related research, text-mining, Web page retrieval and dialogue systems … FastText 5.1 Introduction Recently there are many text classification models based on neural networks become increasingly popular …

Robust Task Clustering for Deep and Diverse Multi-Task and Few-Shot Learning
M Yu, X Guo, J Yi, S Chang, S Potdar, G Tesauro… – 2017 – openreview.net
… Data Sets We test our methods by conducting experiments on three text classification data sets … 2. Diverse Real-World Tasks: User Intent Classification for Dialog System The second dataset is from an on-line service which trains and serves intent classification models to various …

Actionable Email Intent Modeling with Reparametrized RNNs
CC Lin, D Kang, M Gamon, M Khabsa… – arXiv preprint arXiv …, 2017 – arxiv.org
Page 1. Actionable Email Intent Modeling with Reparametrized RNNs Chu-Cheng Lin? Johns Hopkins University Baltimore, MD clin103@jhu.edu Dongyeop Kang Carnegie Mellon University Pittsburgh, PA dongyeok@cs.cmu.edu …

Opinion Mining in Twitter: How to make use of Sarcasm to Enhance Sentiment Analysis: A
S Parveen, A Surnar, S Sonawane – ijarcet.org
… However, tweets have been used more by researchers for text classification and sentiment analysis … Association for Computational Linguistics [4] Joseph Tepperman, DR “Yeah right: sarcasm recognition for spoken dialogue systems”, In Proceedings of INTERSPEECH [5] CC …

Language Technology for Polish in Practice
M Piasecki, M Maziarz, M Marci?czuk, M Oleksy – CLARIN, 2017 – clarin-pl.eu
Page 1. CLARIN-PL Language Technology for Polish in Practice Basic language resources for Polish Maciej Piasecki, Marek Maziarz, Marcin Oleksy, Ewa Rudnicka Wroc?aw University of Science and Technology G4.19 Research Group …

Automatic problem extraction and analysis from unstructured text in IT tickets
S Agarwal, V Aggarwal, AR Akula… – IBM Journal of …, 2017 – ieeexplore.ieee.org
… A comprehensive list is shown in Table 1. There were multiple problems with using off-the-shelf text-classification approaches on these tickets. The description field is extremely noisy, with no neat regular expression that can capture it …

Active learning in annotating micro-blogs dealing with e-reputation
JV Cossu, A Molina-Villegas… – arXiv preprint arXiv …, 2017 – arxiv.org
… same for others. Multilingual aspects, cultural factors and context awareness are among the main challenges of sentiment natural language text classification when dealing with reputational micro-blogs. Furthermore, topic detection …

Natural Language Processing: State of The Art, Current Trends and Challenges
D Khurana, A Koli, K Khatter, S Singh – arXiv preprint arXiv:1708.05148, 2017 – arxiv.org
… (Fang et al. 2015 [72]) 6.6 Dialogue System … It is believed that these dialogue systems when utilizing all levels of language processing offer potential for fully automated dialog systems. (Elizabeth D. Liddy, 2001) [7]. Whether on text or via voice …

Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers
M Lapata, P Blunsom, A Koller – Proceedings of the 15th Conference of …, 2017 – aclweb.org
… 427 A Network-based End-to-End Trainable Task-oriented Dialogue System Tsung-Hsien Wen, David Vandyke, Nikola Mrkšic, Milica Gasic, Lina M. Rojas Barahona, Pei-Hao Su, Stefan Ultes and Steve Young …

Sarcasm Identification on Twitter: A Machine Learning Approach
A Onan – Computer Science On-line Conference, 2017 – Springer
… Tepperman, J., Traum, DR, Narayanan, S.: “yeah right”: sarcasm recognition for spoken dialogue systems. In: Proceedings of the Ninth International Conference on Spoken Language Processing, pp … Aggarwal, CC, Zhai, CX: A survey of text classification algorithms …

An Efficient Approach for Sarcasm Recognition on Twitterusing Pattern-Based Method
K ShehlaKulsum, SG Vaidya – ijarcet.org
… 106 All Rights Reserved © 2017 IJARCET dialogue systems, opinion oriented summarization[16], etc.because of inability to detect sarcastic comments … Sriram et al. [9] proposed a method for short text classification on Twitter to improve information filtering …

Bringing Semantic Structures to User Intent Detection in Online Medical Queries
C Zhang, N Du, W Fan, Y Li, CT Lu, PS Yu – arXiv preprint arXiv …, 2017 – arxiv.org
Page 1. Bringing Semantic Structures to User Intent Detection in Online Medical Queries Chenwei Zhang?¶, Nan Du†, Wei Fan‡, Yaliang Li†, Chun-Ta Lu?, Philip S. Yu?§ ? Department of Computer Science, University of Illinois …

Character-based Embedding Models and Reranking Strategies for Understanding Natural Language Meal Descriptions
M Korpusik, Z Collins, J Glass – Proc. Interspeech 2017, 2017 – groups.csail.mit.edu
… [20] X. Zhang, J. Zhao, and Y. LeCun, “Character-level convolutional networks for text classification,” in Proceedings of Advances in neural … [24] M. Korpusik and J. Glass, “Spoken language understanding for a nutrition dialogue system,” IEEE Transactions on Audio, Speech …

Question Answering System: A Review On Question Analysis, Document Processing, And Answer Extraction Techniques.
FS UTOMO, N SURYANA… – Journal of Theoretical & …, 2017 – search.ebscohost.com
Page 1. Journal of Theoretical and Applied Information Technology 31st July 2017. Vol.95. No 14 © 2005 – ongoing JATIT & LLS ISSN: 1992-8645 www.jatit.org E-ISSN: 1817-3195 3158 QUESTION ANSWERING SYSTEM : A REVIEW ON …

Implementation of robot journalism by programming custombot using tokenization and custom tagging
N Lee, K Kim, T Yoon – Advanced Communication Technology …, 2017 – ieeexplore.ieee.org
… Text Classification is the task which 567 ISBN 978-89-968650-9-4 ICACT2017 February 19 ~ 22, 2017 Page 3 … Semantic Role Labelling is also used for Dialogue System; it is a task which identifies sentence elements such as subject and object in each sentence [15] …

Addressing challenges in promoting healthy lifestyles: the al-chatbot approach
A Fadhil, S Gabrielli – Proceedings of the 11th EAI International …, 2017 – dl.acm.org
… [7] Forman, G. 2003. An extensive empirical study of feature selection metrics for text classification. J. Mach. Learn. Res … DOI= http://doi.acm.org/10.1145/964696.964697. [14] Alvarez-Godinez, Eduardo, and Sumithra Bhakthavatsalam. “Anna: A Nutrition-Facts Dialogue System.”

Ensemble application of convolutional neural networks and multiple kernel learning for multimodal sentiment analysis
S Poria, H Peng, A Hussain, N Howard, E Cambria – Neurocomputing, 2017 – Elsevier
Skip to main content …

Unbounded cache model for online language modeling with open vocabulary
E Grave, MM Cisse, A Joulin – Advances in Neural Information …, 2017 – papers.nips.cc
… [30] A. Joulin, E. Grave, P. Bojanowski, M. Douze, H. Jégou, and T. Mikolov. Fasttext.zip: Compressing text classification models. arXiv preprint arXiv:1612.03651, 2016 … Building end-to-end dialogue systems using generative hierarchical neural network models. In AAAI, 2016 …

Natural language processing in mental health applications using non-clinical texts
RA Calvo, DN Milne, MS Hussain… – Natural Language …, 2017 – cambridge.org
… Section 4 describes the techniques that researchers have applied to make inferences or generate diagnoses about the emotional state or mental health of the authors of these texts. This work draws widely upon text classification and NLP …

Evaluation of Modern Tools for an OMSCS Advisor Chatbot
E Gregori – 2017 – smartech.gatech.edu
… VPINO is a coaching/counseling chatbot based on IBM’s Watson. “?A text based natural language dialogue system specifically developed for the purpose of holding structured, goal directed coaching conversations … [55] FastText also supports text classification …

Distinguishing between facts and opinions for sentiment analysis: Survey and challenges
I Chaturvedi, E Cambria, RE Welsch, F Herrera – Information Fusion, 2017 – Elsevier
… Furthermore, subjective extracts are only 60% of the review and produce the same polarity results are full text classification [13] … financial [29] and political [30] forecasting, e-health [31] and e-tourism [32], human communication comprehension [33] and dialogue systems [34], etc …

Detecting sarcasm in customer tweets: an NLP based approach
S Mukherjee, PK Bala – Industrial Management & Data Systems, 2017 – emeraldinsight.com
… Despite the difficulties, the huge benefit of detecting sarcasm has been recognized in many computer interaction-based applications, such as review summarization, dialogue systems and review ranking systems (Davidov et al., 2010) …

Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
R Barzilay, MY Kan – Proceedings of the 55th Annual Meeting of the …, 2017 – aclweb.org
Page 1. ACL 2017 The 55th Annual Meeting of the Association for Computational Linguistics Proceedings of the Conference, Vol. 1 (Long Papers) July 30 – August 4, 2017 Vancouver, Canada Page 2. Platinum Sponsors: Gold Sponsors: ii Page 3. Silver Sponsors …

Active Learning for Visual Question Answering: An Empirical Study
X Lin, D Parikh – arXiv preprint arXiv:1711.01732, 2017 – arxiv.org
… shallow models. For deep models however, active learning literature is scarce and mainly focuses on classical unimodal tasks such as image and text classification. In this work we study active learning for deep VQA models. VQA …

Sentence?Chain Based Seq2seq Model for Corpus Expansion
E Chung, JG Park – ETRI Journal, 2017 – Wiley Online Library
By continuing to browse this site you agree to us using cookies as described in About Cookies. Remove maintenance message …

Incorporating Structural Bias into Neural Networks
Z Yang – 2017 – cs.cmu.edu
Page 1. November 2, 2017 DRAFT Thesis Proposal Incorporating Structural Bias into Neural Networks Zichao Yang Nov 2017 School of Computer Science Carnegie Mellon University Pittsburgh, PA 15213 Thesis Committee …

An Empirical Study on Incorporating Prior Knowledge into BLSTM Framework in Answer Selection
Y Li, M Yang, T Zhao, D Zheng, S Li – National CCF Conference on …, 2017 – Springer
… 2016) conduct short text classification base on CNN, and expand the short text with synonym as information … A comprehensive view demands further examination of this issue in other NLP tasks such as MT, dialogue system etc …

Developing Virtual Patients with VR/AR for a natural user interface in medical teaching
MA Zielke, D Zakhidov, G Hardee… – Serious Games and …, 2017 – ieeexplore.ieee.org
… ICT’s VHTK includes: Multisense -tracks and analyzes users’ facial expressions, body posture, acoustic features, linguistic patterns and higher level behavior descriptors (eg attention, fidgeting); the NPCEditor — a statistical text classification algorithm that selects the character’s …

Salience based lexical features for emotion recognition
KW Gamage, V Sethu… – Acoustics, Speech and …, 2017 – ieeexplore.ieee.org
… Bag-of-n-grams [9, 12] and their refinements such as log term frequency (log TF) [13], adopted from text classification are the … [5] J. Liscombe, G. Riccardi and D. Hakkani-Tur, “Using Context to Improve Emotion Detection in Spoken Dialog Systems”, Academiccommons.columbia …

A joint deep model of entities and documents for cumulative citation recommendation
L Ma, D Song, L Liao, Y Ni – Cluster Computing, 2017 – Springer
… Kim [22] presents a simple convolutional neural networks (CNN) with one layer of convolution on top of word vectors for text classification. Kalchbrenner et al … Lee and Dernoncourt [29] introduce a model based on RNN and CNN for sequential short-text classification …

Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
M Palmer, R Hwa, S Riedel – Proceedings of the 2017 Conference on …, 2017 – aclweb.org
Page 1. EMNLP 2017 The Conference on Empirical Methods in Natural Language Processing Proceedings of the Conference September 9-11, 2017 Copenhagen, Denmark Page 2. c?2017 The Association for Computational Linguistics …

Recommending social platform content using deep learning
J JAXING, A HÅKANSSON, M GORETSKYY… – publications.lib.chalmers.se
… The model does not show any real advantages in its current state but a lot of potential improvements are proposed. Keywords: Artificial Neural Networks, ANN, Recurrent Neural Networks, RNN, Recommender Systems, Automatic Recommendations, Text Classification iii …

Information Retrieval Models: Trends and Techniques
S Krishnamurthy, V Akila – Web Semantics for Textual and Visual …, 2017 – igi-global.com
… It is mostly adopted in many systems like library OPAC’s, dialog systems and few search engines … The name of people, names of locations company name dates are referred to as named entities the text classification algorithms Sambyal et al (2016) are used to classify the topics …

Modelling semantic context of oov words in large vocabulary continuous speech recognition
I Sheikh, D Fohr, I Illina… – IEEE/ACM Transactions on …, 2017 – ieeexplore.ieee.org
… Com- pared to these works, we explore neural network models trained to retrieve relevant OOV PNs for audio documents with a single news event. Our methodology in this paper is related to the recent ap- proaches for text classification with neural networks …

Multimodal Crowdsourcing for Transcribing Handwritten Documents
E Granell, CD Martinez-Hinarejos – IEEE/ACM Transactions on …, 2017 – ieeexplore.ieee.org
Page 1. IEEE/ACM TRANSACTIONS ON AUDIO, SPEECH, AND LANGUAGE PROCESSING, VOL. 25, NO. 2, FEBRUARY 2017 409 Multimodal Crowdsourcing for Transcribing Handwritten Documents Emilio Granell and Carlos-D. Mart?nez-Hinarejos …

Emotion Recognition: A Literature Survey
S Goyal, N Tiwari – International Journal For Technological Research In … – ijtre.com
… Goal: artificial intelligence, robotics, psychology blogs, product reviews, CRM and service oriented companies, customer emotion. Applications: automatic answering systems, dialogue systems, and human like robots. Multi- Language Text …

The Emotional Impact of Audio-Visual Stimuli
TP Thomas – 2017 – search.proquest.com
… a man is looking at something. 5 a woman is slicing a piece of a knife it is a scene of a field. The Text classification model with the text descriptions from the MSVD trained … The Text classification model with text descriptions extracted using the S2VT …

Tag Recommendation for Short Arabic Text by Using Latent Semantic Analysis of Wikipedia 
YKA Samra, IM Alagha – 2017 – mobt3ath.com
Page 1. Tag Recommendation for Short Arabic Text by Using Latent Semantic Analysis of Wikipedia Yousef K. Abu Samra Supervised By: Dr. Iyad M. Alagha Assistant Professor of Computer Science …

Sabbiu Shah (070/BCT/531) Sagar Adhikari (070/BCT/533) Samip Subedi (070/BCT/536)
U Chalise – 2017 – researchgate.net
… human would behave as a conversational partner, thereby passing the Turing test. Chatterbots are typically used in dialog systems for various practical purposes including customer service or information acquisition. The classic …

Automatic Text Simplification
H Saggion – Synthesis Lectures on Human Language …, 2017 – morganclaypool.com
… Semantic Role Labeling Martha Palmer, Daniel Gildea, and Nianwen Xue 2010 Spoken Dialogue Systems Kristiina Jokinen and Michael McTear 2009 Introduction to Chinese Natural Language Processing Kam-Fai Wong, Wenjie Li, Ruifeng Xu, and Zheng-sheng Zhang 2009 …

Refining Word Embeddings Using Intensity Scores for Sentiment Analysis
LC Yu, J Wang, KR Lai, X Zhang – researchgate.net
… named entity recognition [18], word sense disambiguation [19], dependency parsing [20], machine translation [21], text classification [22], and … injected both antonymy and synonymy relations into vector representations to improve the capability of dialog systems for distinguishing …

Deep Memory Networks for Natural Conversations
??? – 2017 – s-space.snu.ac.kr
… 76 Page 8. v List of Tables [Table 3.1] Evaluation results of multi-class text classification ….. 27 [Table 3.2] Nearest neighbor words by Skip-Gram and Dependency-gram ….. 28 …

Deriving and Exploiting Situational Information in Speech: Investigations in a Simulated Search and Rescue Scenario
S Mokaram Ghotoorlar – 2017 – etheses.whiterose.ac.uk
Page 1. Deriving and Exploiting Situational Information in Speech: Investigations in a Simulated Search and Rescue Scenario Saeid Mokaram Department of Computer Science The University of Sheffield PhD Thesis submitted for the degree of Doctor of Philosophy …

Monday, May 15, 2017
SL Datasets, BD Analytics – ieeexplore.ieee.org
Page 1. TECHNICAL PAPERS Scroll to the title and select a Blue link to open a paper. After viewing the paper, use the bookmarks to the left to return to the beginning of the Table of Contents. Monday, May 15, 2017 Session …

Learning Logic Rules From Text Using Statistical Methods For Natural Language Processing
M KAZMI – 2017 – peterschueller.com
… (Manning and Schütze, 1999). They tend to place greater importance to Statistical NLP approaches as they are robust in practice. One example of a model in NLP for text classification is the bag-of-words model. In this model …

Clinical event prediction and understanding with deep neural networks
H Suresh – 2017 – dspace.mit.edu
… LSTMs have achieved state-of-the-art results in many different applications, such as machine translation [11], dialogue systems [12], and image captioning [13] … They were recently used as an initialization step for recurrent neural networks for text classification [15], but …

Advanced data exploitation in speech analysis: An overview
Z Zhang, N Cummins, B Schuller – IEEE Signal Processing …, 2017 – ieeexplore.ieee.org
… For speech processing, crowdsourcing has been widely employed for a range of tasks, including speech data col- lection/acquisition, speech annotation, speech perception, assessment of speech synthesis, and dialog system evalua- tion [15], [26] …

Transparency in Robot Autonomy
MM Veloso – Workshop–Beneficial AI, 2017 – futureoflife.org
Page 1. 1/5/17 1 Manuela M. Veloso Joint work Francesca Rossi, Stephanie Rosenthal, Sai Selvaraj, Vi orio Perera Machine Learning Department Computer Science Department Robo cs Ins tute School of Computer Science Carnegie Mellon University …

Advances in Neural Networks-ISNN 2017: 14th International Symposium, ISNN 2017, Sapporo, Hakodate, and Muroran, Hokkaido, Japan, June 21–26, 2017 …
F Cong, A Leung, Q Wei – 2017 – books.google.com
… Cuihua Ma, Ping Guo, Xin Xin, Xiaoyu Ma, Yanjie Liang, Shaomin Xing, Li Li, and Shaozhuang Liu Text Classification Based on ReLU Activation Function of SAE Algorithm …

A Self-Adaptive Sliding Window Based Topic Model for Non-uniform Texts
J He, L Li, X Wu – Data Mining (ICDM), 2017 IEEE International …, 2017 – ieeexplore.ieee.org
Page 1. A Self-adaptive Sliding Window based Topic Model for Non-uniform Texts Jin He School of Computing and Information HeFei University of Technology Hefei, China, 230009 Email: jinhe@mail.hfut.edu.cn Lei Li School …

Online Help Seeking in Computer Science Education
Q Hao – 2017 – works.bepress.com
Page 1. Western Washington University From the SelectedWorks of Qiang Hao Summer May, 2017 Online help seeking in computer science education Qiang Hao, Western Washington University Available at: https://works.bepress.com/qiang-hao/25/ Page 2 …

Helping users learn about social processes while learning from users: developing a positive feedback in social computing
VSS Pillutla – 2017 – search.proquest.com
… This is accomplished by using a social network analysis in. Chapter 4 and by applying text classification in Chapter 5. The final part of this thesis focuses on … Here, such techniques are represented by text classification. We note that none of these sections …

SingularityNET: A decentralized, open market and inter-network for AIs
B Goertzel, S Giacomelli, D Hanson, C Pennachin… – 2017 – icotokn.com
Page 1. SingularityNET: A decentralized, open market and inter-network for AIs Ben Goertzel, Simone Giacomelli, David Hanson, Cassio Pennachin, Marco Argentieri and the SingularityNET team November 1, 2017 Abstract …

Design and development of a cognitive assistant for the architecting of earth observing satellites
A Virós Martin – 2017 – upcommons.upc.edu
… well as others as seen in [76, 77]. Finally, neural network models have been used for the text classification inside the skill … solution until the state of the art in this field is furthered, instead relying on more classic techniques like text classification, feature extraction and manual …

Lagrangean-Based Combinatorial Optimization for Large-Scale S³VMS
F Bagattini, P Cappanera… – IEEE Transactions on …, 2017 – ieeexplore.ieee.org
… found in [11]. Some real- world applications of semisupervised learning and particularly of S3VMs are [12] (spoken dialogue systems evaluation), [13] (satellite image classification), and [14] (healthcare). II. LAGRANGEAN S3VM …

Computer Vision and Natural Language Processing: Recent Approaches in Multimedia and Robotics
P Wiriyathammabhum, D Summers-Stay… – ACM Computing …, 2017 – dl.acm.org
… Zero-shot learning is very similar to text classification in NLP if attributes are thought of as words in a document, and we are trying to label that document. From this viewpoint, we can incorporate the feature learning framework into attribute-based recognition …

Deep Reinforcement Learning in Natural Language Scenarios
J He – 2017 – digital.lib.washington.edu
… good/bad endings. Another example is a human-computer dialog system, where the action is the response generated by the dialog manager … agation [22] and demonstrated its interpretability on several large-scale text classification tasks [21] …

Natural Language Processing for Social Media
A Farzindar, D Inkpen – Synthesis Lectures on Human …, 2017 – morganclaypool.com
… Semantic Role Labeling Martha Palmer, Daniel Gildea, and Nianwen Xue 2010 Spoken Dialogue Systems Kristiina Jokinen and Michael McTear 2009 Introduction to Chinese Natural Language Processing Kam-Fai Wong, Wenjie Li, Ruifeng Xu, and Zheng-sheng Zhang 2009 …

Analyzing EEG data and improving data partitioning for machine learning algorithms
K Korjus – 2017 – dspace.ut.ee
Page 1. I DISSERTATIONES MATHEMATICAE UNIVERSITATIS TARTUENSIS 121 K R IS T JA NK O R JU S A nalyzing E E GD ata and Im proving D ata Partitioning for M achine L earning A lgorithm s KRISTJAN KORJUS Analyzing EEG Data and …

Linguistic Knowledge Transfer for Enriching Vector Representations
JK Kim – 2017 – rave.ohiolink.edu
Page 1. Linguistic Knowledge Transfer for Enriching Vector Representations DISSERTATION Presented in Partial Fulfillment of the Requirements for the Degree Doctor of Philosophy in the Graduate School of The Ohio State University By Joo-Kyung Kim, BE, MS …

Explanation in artificial intelligence: Insights from the social sciences
T Miller – arXiv preprint arXiv:1706.07269, 2017 – arxiv.org
Page 1. Explanation in Artificial Intelligence: Insights from the Social Sciences Tim Miller School of Computing and Information Systems University of Melbourne, Melbourne, Australia tmiller@ unimelb. edu. au Abstract There …

Neural machine translation and sequence-to-sequence models: A tutorial
G Neubig – arXiv preprint arXiv:1703.01619, 2017 – arxiv.org
Page 1. Neural Machine Translation and Sequence-to-sequence Models: A Tutorial Graham Neubig Language Technologies Institute, Carnegie Mellon University 1 Introduction This tutorial introduces a new and powerful set …

Schedule Highlights
P Sturm – Machine Learning, 2017 – pdfs.semanticscholar.org
… Research community challenge tasks are proliferating, including the sixth Dialog Systems Technology Challenge (DSTC6), the Amazon Alexa prize, and the Conversational Intelligence Challenge live competition at NIPS 2017 …

Automatic Generation of News Comments Based on Gated Attention Neural Networks
HT Zheng, W Wang, W Chen, JY Chen… – IEEE …, 2017 – ieeexplore.ieee.org
… for discrete data. In this paper, we choose the CNN as our discriminator be- cause CNN has recently been shown of great effectiveness in text classification [28]. The discriminator adopts a structure similar to Yu et al. [27] and …

Exploring Cells and Context Approaches for RNN Based Conversational Agents
S Johnsrud, S Christensen – 2017 – brage.bibsys.no
Page 1. Exploring Cells and Context Approaches for RNN Based Conversational Agents Silje Christensen Simen Johnsrud Master of Science in Computer Science Supervisor: Massimiliano Ruocco, IDI Department of Computer Science Submission date: June 2017 …

Neural Logic Framework for Digital Assistants
N Cingillioglu, A Russo, K Broda – 2017 – imperial.ac.uk
Page 1. MEng Individual Project Imperial College London Department of Computing Neural Logic Framework for Digital Assistants Author: Nuri Cingillioglu Supervisor: Prof. Alessandra Russo Second Marker: Dr. Krysia Broda June 16, 2017 Page 2. Abstract …

Multimodal Analysis of User-Generated Multimedia Content
R Shah, R Zimmermann – 2017 – Springer
… Examples of the second domain will include, but not limited to: computational and psychological models of emotions, bodily manifestations of affect (facial expressions, posture, behavior, physiology), and affective interfaces and applications (dialogue systems, games, learning …

Automated Feature Engineering for Deep Neural Networks with Genetic Programming
J Heaton – 2017 – search.proquest.com
… 27. Text classification is another popular application of machine learning algorithms … Representing textual data to a machine learning model produces a considerable number of dimensions. Text classification commonly uses feature engineering to reduce these dimensions …

(Visited 40 times, 1 visits today)