Paraphrasing & Dialog Systems 2019


Notes:

A paraphrase is a restatement of the meaning of a text or passage using other words.

  • Script understanding system

Resources:

Wikipedia:

References:

See also:

100 Best Spintax Videos100 Best WordPress Article Spinning VideosParaphrase DatabaseParaphrase IdentificationSPG (Statistical Paraphrase Generation)


Using Alignments in Automatic Paraphrase Production to Combat Data Sparsity in Question Interpretation for a Virtual Patient Dialogue System
S Ewing – 2019 – kb.osu.edu
… al patients or related dialogue systems. 6.2 Methodology Stats … 2018. Using Para- phrasing and Memory-Augmented Models to Combat Data Sparsity in Question Interpreta- tion with a Virtual Patient Dialogue System … Paraphrasing Revisited with Neural Machine Translation …

Improving Robustness of Task Oriented Dialog Systems
A Einolghozati, S Gupta, M Mohit, R Shah – arXiv preprint arXiv …, 2019 – arxiv.org
… Task oriented language understanding in dialog systems is often modeled using in- tents (task of a query) and slots (parameters for that task … robustness against two types of untargeted (that is, we do not target a particular perturbed label) perturbations: paraphrasing and random …

Using virtual standardized patients to accurately assess information gathering skills in medical students
KR Maicher, L Zimmerman, B Wilcox, B Liston… – Medical …, 2019 – Taylor & Francis
AbstractIntroduction: Practicing a medical history using standardized patients is an essential component of medical school curricula. Recent advances in technology now allow for newer approaches fo…

Conditioned Query Generation for Task-Oriented Dialogue Systems
S d’Ascoli, A Coucke, F Caltagirone, A Caulier… – arXiv preprint arXiv …, 2019 – arxiv.org
… Closed-domain dialogue systems, single- or multi-turn, have become ubiquitous nowadays with the rise of conversational interfaces … In [3] and [4] the authors use variational autoencoders to generate utterances through paraphrasing with the objective of aug- menting the SLU …

Paraphrase generation for semi-supervised learning in nlu
E Cho, H Xie, WM Campbell – Proceedings of the Workshop on Methods …, 2019 – aclweb.org
… language understanding (NLU) technol- ogy is one of the components for dialog systems, producing interpretation for … In this work, we de- fine functionality as a dialog system’s capability … To generate functionality-relevant utterances, we use paraphrasing, a task to gener- ate an …

Data-driven dialogue systems for social agents
KK Bowden, S Oraby, A Misra, J Wu, S Lukin… – … Social Interaction with …, 2019 – Springer
… and many corpora are available for building data-driven dialogue systems [19, 20] … with modules for sentiment analysis and style, topic analysis, summarization, paraphrasing, rephrasing, and … may be of interest for indexing knowledge for a dialogue system, annotations are not …

Analyzing How a Talk Show Host Performs Follow-Up Questions for Developing an Interview Agent
H Narimatsu, R Higashinaka, H Sugiyama, M Mizukami… – workshop.colips.org
… This paper adds interviewing skills to a chat-oriented dialogue system in order to produce more engaging dialogue … 0 0.1 0.2 0.3 0.4 0.5 Filler Repeat Adm iration Paraphrasing Urging FQ Question (Ir) Others … Counseling dialog system with 5w1h extraction. In Proc …

Effective Data Augmentation Approaches to End-to-End Task-Oriented Dialogue
J Quan, D Xiong – 2019 International Conference on Asian …, 2019 – ieeexplore.ieee.org
… For data-driven dialogue systems, especially neural dialogue systems which are more data- hungry, insufficient … and stop-word deletion at the word level, translation and paraphrasing at the … In doing so, we hope to diversify user utterances so that our dialogue system can learn …

A study of incorrect paraphrases in crowdsourced user utterances
MA Yaghoub-Zadeh-Fard, B Benatallah… – Proceedings of the …, 2019 – aclweb.org
… Also known as dialogue systems, virtual assistants, chatbots or simply bots (Campagna et al., 2017 … act datasets can assist in de- tecting this category of the paraphrasing issues … of questions and answers by mining datasets in the fields of Question Answering and dialog systems …

Evaluating a Spoken Dialogue System for Recording Systems of Nursing Care
T Mairittha, N Mairittha, S Inoue – Sensors, 2019 – mdpi.com
… The process of DSCR is slightly different from traditional frame-based dialogue systems because users are unnecessary to complete … In our experiments, we ask 3 users for paraphrasing jobs and ask them to write several constructive paraphrases … Dialogue System Application …

Overview of the NLPCC 2019 Shared Task: Open Domain Semantic Parsing
N Duan – CCF International Conference on Natural Language …, 2019 – Springer
… problem for many artificial intelligence tasks, such as information retrieval, question answering and dialogue system … technologies for building human-machine interaction engines, such as search, question answering and dialogue systems … question paraphrasing/composition …

Conversational Narrative Interfaces for Sensemaking
AO Petac – Proceedings of the 18th International Conference on …, 2019 – ifaamas.org
… We find ourselves at the intersection of four important domains: discourse structure, dialogue systems, inferential pragmatics and narrative generation … In theory, this recognition can be divided into positive proofs (relevant contribution, paraphrasing, repetition or utterances) and …

Decomposable neural paraphrase generation
Z Li, X Jiang, L Shang, Q Liu – arXiv preprint arXiv:1906.09741, 2019 – arxiv.org
… be applied in various downstream tasks such as information retrieval, semantic parsing, and dialogue systems … Phrasal paraphrasing is performed with sen- tence template being fixed … stream applications, for instance, data augmenta- tion in the task-oriented dialogue system …

Zero-Shot Paraphrase Generation with Multilingual Language Models
Y Guo, Y Liao, X Jiang, Q Zhang, Y Zhang… – arXiv preprint arXiv …, 2019 – arxiv.org
… Paraphrasing is to express the same meaning us- ing different expressions. Paraphrase generation plays an important role in various natural language processing (NLP) tasks such as response diversi- fication in dialogue system, query reformulation in information retrieval, and …

An Interactive Mechanism to Improve Question Answering Systems via Feedback
X Zhang, L Zou, S Hu – Proceedings of the 28th ACM International …, 2019 – dl.acm.org
… Session: Long – Question Answering and Dialogue Systems I … Entity/class-Linking Dictionary countries in Europe? Relation-Paraphrasing Dictionary be born (in)? Sentence-Structure Dictionary ?Who verb place …

Fiction Sentence Expansion and Enhancement via Focused Objective and Novelty Curve Sampling
Y Safovich, A Azaria – arXiv preprint arXiv:1912.00698, 2019 – arxiv.org
… We design for some degree of expansion, but same- or reduced-length enhancement (paralleling the tasks of paraphrasing and sentence … Static, human-authored game dialogue systems can be likened to curated interaction with conversational agents, and are an ideal target …

Dstc7 task 1: Noetic end-to-end response selection
C Gunasekara, JK Kummerfeld… – Proceedings of the First …, 2019 – aclweb.org
… also poses a challenge, as the output of an end-to-end dialogue system could be … continuous em- beddings, etc.) that were integrated with end-to- end dialogue systems so as … the source dialogues from training (the actual utterances are different due to paraphrasing), while the …

Content-based table retrieval for web queries
Y Sun, Z Yan, D Tang, N Duan, B Qin – Neurocomputing, 2019 – Elsevier
JavaScript is disabled on your browser. Please enable JavaScript to use all the features on this page. Skip to main content Skip to article …

Proceedings of the 3rd Workshop on Neural Generation and Translation
A Birch, A Finch, H Hayashi, I Konstas… – Proceedings of the 3rd …, 2019 – aclweb.org
… 1 Hello, It’s GPT-2 – How Can I Help You? Towards the Use of Pretrained Language Models for Task- Oriented Dialogue Systems Pawe? Budzianowski and Ivan Vulic … 206 Paraphrasing with Large Language Models Sam Witteveen and Martin Andrews …

Emotion recognition based preference modelling in argumentative dialogue systems
N Rach, K Weber, A Aicher… – 2019 IEEE …, 2019 – ieeexplore.ieee.org
… The respective paraphrasing is done by a template based Natural Language Generation (NLG) that utilizes the … PerDial’19 – The 1st International Workshop on Pervasive Computing and Spoken Dialogue Systems Technology … A human-computer dialogue system for educational …

An adaptable task-oriented dialog system for stand-alone embedded devices
L Duong, VCD Hoang, TQ Pham, YH Hong… – Proceedings of the 57th …, 2019 – aclweb.org
… Intent plus slots representations are stan- dard in many dialog systems, but they cannot ex- press … provide on-line bonuses or penalties, which dramatically reduces spam and improves paraphrasing quality … Dialogue management is central to any task- oriented dialog system …

Data augmentation with atomic templates for spoken language understanding
Z Zhao, S Zhu, K Yu – arXiv preprint arXiv:1908.10770, 2019 – arxiv.org
… The SLU module is a key component of spoken dialogue system, parsing user utterances into cor- responding semantic representations in a narrow domain … Thus, the sentence generator can be an encoder-decoder model, paraphrasing a set of atomic exemplars to an utterance …

Way off-policy batch deep reinforcement learning of implicit human preferences in dialog
N Jaques, A Ghandeharioun, JH Shen… – arXiv preprint arXiv …, 2019 – arxiv.org
… for generative models like dialog systems, which are known to collapse to an uninteresting, small number of repeated samples [34] … similarity (close distance in sentence embedding space [8]) between the human input and agent response, because paraphrasing and style …

Leveraging non-conversational tasks for low resource slot filling: Does it help?
S Louvan, B Magnini – Proceedings of the 20th Annual SIGdial Meeting …, 2019 – aclweb.org
… Slots are typically domain-specific, and adding new domains to a dialogue system in- volves data and time-intensive processes … dialogue systems … In Proceedings of the ACL-PASCAL Workshop on Textual Entailment and Paraphrasing, pages 1–9, Prague …

Iterative delexicalization for improved spoken language understanding
A Ray, Y Shen, H Jin – arXiv preprint arXiv:1910.07060, 2019 – arxiv.org
… intent classification and slot tagging models have achieved tremendous success in recent years for building spoken language understanding and dialog systems … End-to-end task-completion neural dialogue systems … Robust spoken language understanding via paraphrasing …

ParaBank: Monolingual bitext generation and sentential paraphrasing via lexically-constrained neural machine translation
JE Hu, R Rudinger, M Post, B Van Durme – Proceedings of the AAAI …, 2019 – aaai.org
… 2.1 Paraphrasing Resources Lexical Resources WordNet (Miller, 1995) includes manually-curated sub-sentential paraphrases … Positional Constraints It has been observed that RNN de- coders in dialogue systems can be nudged toward produc- ing more diverse outputs by …

Automatically learning data augmentation policies for dialogue tasks
T Niu, M Bansal – arXiv preprint arXiv:1909.12868, 2019 – arxiv.org
… 2We did not use their Generative Paraphrasing where number of changes (which signifies the intensity of the pol- icy) does not apply to this operation, because this operation can … 2016. Building end-to-end dialogue systems using gener- ative hierarchical neural network models …

Multi-domain Conversation Quality Evaluation via User Satisfaction Estimation
PK Bodigutla, L Polymenakos, S Matsoukas – arXiv preprint arXiv …, 2019 – arxiv.org
… turn and dialogue level quality evaluation of end user interactions with Spoken Dialogue Systems (SDS) is … into five groups: 1) Using sparse sentiment for end-to-end dialogue system training; 2 … we design five new feature sets, which are: 1) user request paraphrasing indicators, 2 …

Enhancing Emotional Effectiveness of Virtual-Reality Experiences with Voice Control Interfaces
H Osking, JA Doucette – International Conference on Immersive Learning, 2019 – Springer
… a way to test the immersive elements of Augmented Reality (AR) [6] and dialogue systems [15], to … The game’s branching dialogue system was controlled using the Articy editor, a tool for … into paraphrased quotations (each of the participants consented to this paraphrasing of their …

Neural Poetry: Learning to Generate Poems Using Syllables
A Zugarini, S Melacci, M Maggini – International Conference on Artificial …, 2019 – Springer
… NLG is crucial for multiple NLP applications and problems, such as dialogue systems [20], text summarization [4], and text paraphrasing [7]. Poem generation is an instance of NLG that is particularly fascinating for its peculiar features …

Domain-Independent turn-level Dialogue Quality Evaluation via User Satisfaction Estimation
PK Bodigutla, L Wang, K Ridgeway, J Levy… – arXiv preprint arXiv …, 2019 – arxiv.org
… dialogue level quality evalu- ation of end user interactions with spoken dialogue systems is vital … into 4 groups: 1) Using sparse sentiment for end-to-end dialogue system training; 2 … following 5 sets of domain-independent features: 1. User request paraphrasing – Calculated by …

A crowd-based evaluation of abuse response strategies in conversational agents
AC Curry, V Rieser – arXiv preprint arXiv:1909.04387, 2019 – arxiv.org
… Only the commercial systems and ALICE occasionally offered a second reply, but usually just paraphrasing the original reply … Real user evaluation of a pomdp spoken dialogue system using automatic belief compression … Ethical challenges in data-driven dialogue systems …

Enhancing domain-specific supervised natural language intent classification with a top-down selective ensemble model
GB Jenset, B McGillivray – Machine Learning and Knowledge Extraction, 2019 – mdpi.com
… is an important factor in creating a satisfactory user experience in a production dialogue system … Applications of dialogue systems in highly-regulated domains face the potential added challenge of … Mechanical Turk (AMT), using a mixture of scenario and paraphrasing prompts …

Exploring language style in chatbots to increase perceived product value and user engagement
E Elsholz, J Chamberlain, U Kruschwitz – Proceedings of the 2019 …, 2019 – dl.acm.org
… KEYWORDS Chatbots, Dialogue system, Styled conversational interface, Con- versational agent, Language style transfer, Shakespeare ACM … user interface of the experiment may not necessarily be generalisable to other dialogue systems, where the … Paraphrasing for style …

Towards Diverse Paraphrase Generation Using Multi-Class Wasserstein GAN
Z An, S Liu – arXiv preprint arXiv:1909.13827, 2019 – arxiv.org
… An additional transcoder is used to convert a sentence into its paraphrasing latent code … generation of a given sentence is an important NLP task, which can be applied in many fields such as information retrieval, question answering, text sum- marization, dialogue system, etc …

Cgmh: Constrained sentence generation by metropolis-hastings sampling
N Miao, H Zhou, L Mou, R Yan, L Li – … of the AAAI Conference on Artificial …, 2019 – aaai.org
… We evaluate our method on a variety of tasks, in- cluding keywords-to-sentence generation, unsupervised sen- tence paraphrasing, and unsupervised sentence error correc- tion … 2016) and dialog systems (Mou et al. 2016) …

Joint learning of question answering and question generation
Y Sun, D Tang, N Duan, T Qin, S Liu… – … on Knowledge and …, 2019 – ieeexplore.ieee.org
Page 1. Joint Learning of Question Answering and Question Generation Yibo Sun , Duyu Tang, Nan Duan, Tao Qin, Member, IEEE, Shujie Liu, Zhao Yan , Ming Zhou, Yuanhua Lv, Wenpeng Yin, Xiaocheng Feng, Bing Qin, and Ting Liu …

Outlier detection for improved data quality and diversity in dialog systems
S Larson, A Mahendran, A Lee, JK Kummerfeld… – arXiv preprint arXiv …, 2019 – arxiv.org
… mainly been studied at the document level (Guthrie et al., 2008; Zhuang et al., 2017), whereas texts in dialog systems are often … We build on prior work employing online crowd workers to create data by paraphrasing … two dialog system tasks: intent classification and slot-filling …

Submodular optimization-based diverse paraphrasing and its effectiveness in data augmentation
A Kumar, S Bhattamishra, M Bhandari… – Proceedings of the 2019 …, 2019 – aclweb.org
… How- ever, majority of the prior works in this area have focused on the task of producing diverse responses in dialog systems (Li et al., 2016; Ritter et al., 2011) and not paraphrasing. Given the lack of rel- evant baselines, we compare our model against the following methods …

Deciphering and Analyzing Software Requirements employing the techniques of Natural Language Processing
KA Memon, X Xiaoling – Proceedings of the 2019 4th International …, 2019 – dl.acm.org
… Dialog systems support information extraction and information retrieval easily from customers and more exact information is collected [14] in this way … 2019 Feb 5. [6] Callison-Burch C, Van Durme B. Large-Scale Paraphrasing for Natural Language Understanding …

Unsupervised paraphrasing by simulated annealing
X Liu, L Mou, F Meng, H Zhou, J Zhou… – arXiv preprint arXiv …, 2019 – arxiv.org
… Paraphrasing aims to restate one sentence as another with the same meaning, but different wordings. It constitutes a corner stone in many NLP tasks, such as question answering (Mck- eown 1983), information retrieval (Knight and Marcu 2000), and dialogue systems (Shah et …

Knowledge graph construction and applications for Web search and beyond
P Wang, H Jiang, J Xu, Q Zhang – Data Intelligence, 2019 – MIT Press
… 600 million entity links. We also introduce three applications of knowledge graph in Sogou Inc.: entity detection and linking, knowledge based question answering and knowledge based dialog system. These applications have …

Unified language model pre-training for natural language understanding and generation
L Dong, N Yang, W Wang, F Wei, X Liu… – Advances in Neural …, 2019 – papers.nips.cc
Paper accepted and presented at the Neural Information Processing Systems Conference (http://nips.cc/).

Exploring diverse expressions for paraphrase generation
L Qian, L Qiu, W Zhang, X Jiang, Y Yu – Proceedings of the 2019 …, 2019 – aclweb.org
… as machine translation (Bahdanau et al., 2014; Cho et al., 2014), text summarization (Nallapati et al., 2016) and dialogue systems (Serban et al … prior paraphrase generation method- s mainly consider only one single output for each input, the nature of paraphrasing indicates that …

VICA, a visual counseling agent for emotional distress
Y Sakurai, Y Ikegami, M Sakai, H Fujikawa… – Journal of Ambient …, 2019 – Springer
… Statistical significance of difference in length of interactions involving the same users shows that modern dialogue systems are a substantial, though not … c. Generation of reply response and logs using regular matching rules and accompanied procedures for paraphrasing (incl …

More general evaluation of a client-centered counseling agent
T Horii, Y Sakurai, E Sakurai, S Tsuruta… – 2019 IEEE World …, 2019 – ieeexplore.ieee.org
… Simple paraphrasing … In comparison with CRECA, VCA has been improved to gather information of users in natural conversation, and has improved the versatility as a dialogue system, such as … [11] S. Han, K. Lee, D. Lee, GG Lee, “Counseling Dialog System with 5W1H …

Machines getting with the program: Understanding intent arguments of non-canonical directives
WI Cho, YK Moon, S Moon, SM Kim, NS Kim – arXiv preprint arXiv …, 2019 – arxiv.org
… Keywords: intent argument extraction, paraphrasing, annotation, generation, non-canonical directives … There have been stud- ies on paraphrasing of questions with regard to the core content (Dong et al., 2017), but little has been done on its structured formalization …

Paraphrase generation with latent bag of words
Y Fu, Y Feng, JP Cunningham – Advances in Neural Information …, 2019 – papers.nips.cc
… CoRR, abs/1409.0473, 2015. [3] Igor A Bolshakov and Alexander Gelbukh. Synonymous paraphrasing using wordnet and internet … CoRR, abs/1611.01144, 2017. [21] David Kauchak and Regina Barzilay. Paraphrasing for automatic evaluation …

Dialogue Model and Response Generation for Emotion Improvement Elicitation
N Lubis, S Sakti, K Yoshino, S Nakamura – ahcweb01.naist.jp
… 3) We simulate this model in a dialogue system interaction using language modeling and … a structure will provide an essential framework or design in constructing dialogue systems capable of … Paraphrasing: Restate succinctly what the participant has said as a way of confirming …

Response generation by context-aware prototype editing
Y Wu, F Wei, S Huang, Y Wang, Z Li, M Zhou – Proceedings of the AAAI …, 2019 – aaai.org
Page 1. The Thirty-Third AAAI Conference on Artificial Intelligence (AAAI-19) Response Generation by Context-Aware Prototype Editing Yu Wu,† Furu Wei,‡ Shaohan Huang,‡ Yunli Wang,† Zhoujun Li,†? Ming Zhou‡ †State …

A survey on question answering systems over linked data and documents
E Dimitrakis, K Sgontzos, Y Tzitzikas – Journal of Intelligent Information …, 2019 – Springer
… Dialogue Systems A Dialogue System (DS) is a computer system designed to converse with a human … Spoken Dialogue Systems A Spoken Dialogue System (SDS) is a computer system that takes as input, and provides as output, voice, in order to converse with a human …

Tracy: Tracing facts over knowledge graphs and text
MH Gad-Elrab, D Stepanova, J Urbani… – The World Wide Web …, 2019 – dl.acm.org
… Due to the increasing usage of KGs for tasks like query-answering, dialog systems, etc., it is important to validate each candidate fact to … The main idea con- sists of first converting the SPO query into a textual representation (ie, verbalization) using a paraphrasing dictionary …

Speak to your software visualization—exploring component-based software architectures in augmented reality with a conversational interface
P Seipel, A Stock, S Santhanam… – 2019 Working …, 2019 – ieeexplore.ieee.org
… This problem of paraphrasing user input was already addressed in several works and resolved by using embedding-based techniques [14], [4]. We … To have an engaging conversation, the dialog system should be able to respond to and ask the user in a human readable format …

Lithium-Ion Batteries
B Writer – A Machine-Generated Summary of Current Research …, 2019 – Springer
… market reports or auto-produced weather forecast (data-to-text), automated medical reviews and not to forget the remarkable progress in dialog systems (chat bots … 1. document clustering and ordering, 2. extractive summarization, and 3. paraphrasing of the generated extracts …

Question Answering Systems Approaches and Challenges
R Alqifari – Proceedings of the Student Research Workshop …, 2019 – aclweb.org
… Standard question answering, where the an- swer comes from the KB or a free text. • Dialog systems or chatbots are the system used for chatting with an agent … Paraphrasing: A single sentence in the article may entail or paraphrase the question …

Implementation of an Artificial Conversation Companion
S Höhn – Artificial Companion for Second Language …, 2019 – Springer
… The dataset collected for this work contains only a small number of instances of OISR where paraphrasing or split-reuse is used for explanations … Paraphrasing as a repair carry-out strategy is useful for chatbot utterances that contain collocations …

Coqa: A conversational question answering challenge
S Reddy, D Chen, CD Manning – Transactions of the Association for …, 2019 – MIT Press
Create a new account. Email. Returning user. Can’t sign in? Forgot your password? Enter your email address below and we will send you the reset instructions. Email. Cancel. If the address matches an existing account you will …

Curio SmartChat: A system for Natural Language Question Answering for Self-Paced K-12 Learning
S Raamadhurai, R Baker, V Poduval – … on Innovative Use of NLP for …, 2019 – aclweb.org
… little effort to scale these systems, with considerably more energy going into tutor-led tutorial dialogue systems (Wolfe et al … Using Paraphrasing and Memory- Augmented Models to Combat Data Sparsity in Question Interpretation with a Virtual Patient Dialogue System …

Exploring the Role of Common Model of Cognition in Designing Adaptive Coaching Interactions for Health Behavior Change
S Mohan – arXiv preprint arXiv:1910.07728, 2019 – arxiv.org
… Prior work[41] has studied how conversational agents and dialog systems can be used for motivational interviewing (MI) to promote … the agent can use facial gestures to display affective empathy and can demonstrate verbal reflexive listening by paraphrasing and summarizing …

Cross-Lingual Semantic Similarity in Pieces of Al-Quran Verses Translation Using Word Alignment and Semantic Vector Approach
R Amelia, MA Bijaksana – International Seminar on …, 2019 – journal.ittelkom-sby.ac.id
… including image captions, news headlines, Wikipedia articles, news, and new genres like answers from a tutorial dialogue systems, answers from … is the approach used to address limitations in word alignment which can only identify the word semantics for lexical paraphrasing …

(Male, Bachelor) and (Female, Ph. D) have different connotations: Parallelly Annotated Stylistic Language Dataset with Multiple Personas
D Kang, V Gangal, E Hovy – arXiv preprint arXiv:1909.00098, 2019 – arxiv.org
… setup mostly preserves the meaning by simply paraphrasing the sentence, but annotators’ per- sonal style does not reflect the variation. With a single image, on the other hand, the outputs pro- duced by annotators tend to be diverse …

Handling divergent reference texts when evaluating table-to-text generation
B Dhingra, M Faruqui, A Parikh, MW Chang… – arXiv preprint arXiv …, 2019 – arxiv.org
Page 1. Handling Divergent Reference Texts when Evaluating Table-to-Text Generation Bhuwan Dhingra† ? Manaal Faruqui‡ Ankur Parikh‡ Ming-Wei Chang‡ Dipanjan Das‡ William W. Cohen†‡ † Carnegie Mellon University …

Using Lucene for Developing a Question-Answering Agent in Portuguese
H Gonçalo Oliveira, R Filipe… – 8th Symposium on …, 2019 – drops.dagstuhl.de
… smartphones, smartwatches or smart homes. In fact, since ELIZA [22], chatbots and dialog systems have become more human-like, able to engage in informal conversations and to learn from user input. This shift is so present …

Moverscore: Text generation evaluating with contextualized embeddings and earth mover distance
W Zhao, M Peyrard, F Liu, Y Gao, CM Meyer… – arXiv preprint arXiv …, 2019 – arxiv.org
… If n > 1, n- gram embeddings are calculated by Eq. (1). Note that they represent sentence embeddings when n = size of the sentence. Fine-tuning Tasks Natural Language Inference (NLI) and paraphrasing pose high demands in understanding sentence meaning …

Long Term Memory in Conversational Robots
J Olson, E Södergren – 2019 – diva-portal.org
… This makes enhanced dialogue system interaction even more interesting to examine from a business perspective … While the development of interactive dialogue systems certainly has moved forward a great deal in recent years, due to the research regarding deep learning and …

Other-Initiated Self-Repair with Linguistic Trouble Source
S Höhn – Artificial Companion for Second Language …, 2019 – Springer
… strategies depend on the type of the trouble source and the repair initiation format. As explained earlier, in Section 4.2, some of the repair initiations require a yes/no answer, and some of them require definition work or paraphrasing of the trouble source …

Knowledge-based Conversational Search
S Vakulenko – arXiv preprint arXiv:1912.06859, 2019 – arxiv.org
… 6.3 End-to-end Methodology for Designing a Dialogue System … makes them reminiscent of the traditional command-line interfaces enhanced with some paraphrasing and speech … applied to characterize a dialogue phenomena and inform the design of dialogue systems [171] …

Crowdsourcing a High-Quality Gold Standard for QA-SRL
P Roit, A Klein, D Stepanov, J Mamou… – arXiv preprint arXiv …, 2019 – arxiv.org
… further corrected the evaluation deci- sions, accounting for some automatic evaluation mistakes introduced by the span-matching and question paraphrasing criteria … Unsupervised induction and filling of semantic slots for spoken dialogue systems using frame-semantic parsing …

The State of Speech in HCI: Trends, Themes and Challenges
L Clark, P Doyle, D Garaialde, E Gilmartin… – Interacting with …, 2019 – academic.oup.com
AbstractSpeech interfaces are growing in popularity. Through a review of 99 research papers this work maps the trends, themes, findings and methods of empirical.

FAMULUS: interactive annotation and feedback generation for teaching diagnostic reasoning
J Pfeiffer, CM Meyer, C Schulz, J Kiesewetter… – arXiv preprint arXiv …, 2019 – arxiv.org
… Frontline Learning Research, 4:28–45. Lifeng Jin, David King, Amad Hussein, Michael White, and Douglas Danforth. 2018. Using Paraphrasing and Memory-Augmented Models to Combat Data Sparsity in Question Interpretation with a Virtual Pa- tient Dialogue System …

Sketching NLP: a case study of exploring the right things to design with language intelligence
Q Yang, J Cranshaw, S Amershi, ST Iqbal… – Proceedings of the 2019 …, 2019 – dl.acm.org
… to human utterances [3]. Some examples of modern canonical NLP problems are information retrieval, machine translation, dialogue systems, and question … require labelling (to learn these)” (Designer note, week 7). Take the aforementioned design idea “paraphrasing in a more …

Understanding and Generating Multi-Sentence Texts
RK Kedziorski – 2019 – digital.lib.washington.edu
… Techniques for such synthesis, however, are necessary for improved language understanding and have the potential to transform downstream applications including dialog systems, question answering, and educational technologies. In this thesis, I …

A COMPREHENSIVE STUDY OF SHALLOW PARSING AND MACHINE TRANSLATIN IN MALAYLAM
R Sankaravelayuthan, K Krishnakumar – researchgate.net
Page 1. 1 A COMPREHENSIVE STUDY OF SHALLOW PARSING AND MACHINE TRANSLATION IN MALAYLAM Prof. Rajendran Sankaravelayuthan Amrita Vishwa Vidyapeetham, Coimbatore rajushush@gmail.com Dr. Krishnakumar …

Automated Approaches to Community Question Answering
A Uva – 2019 – eprints-phd.biblio.unitn.it
… The latter can be used to quickly bootstrap Natural Language Understanding pipelines for dialog systems. To conclude, we study advantages and disadvantages of neural networks and tree kernel models when applied to cQA tasks …

Multitask learning approach for understanding the relationship between two sentences
HS Choi, H Lee – Information Sciences, 2019 – Elsevier
… example, these tasks have been leveraged for applications such as document summarization, text generation, semantic search, dialog system, question answering … In this layer, our objective for each task is to find the relationship, detect paraphrasing, and measure the similarity …

Accelerating conversational agents built with off-the-shelf modularized services
J Lee, I Hwang, TS Hubregtsen… – IEEE Pervasive …, 2019 – ieeexplore.ieee.org
… language processing (NLP): Takes input of the transcribed utterances; and out- puts a key intent embedded in the utterance despite possible different paraphrasing … Estimated Speedup Using modularized services, the latency Lbase of the baseline dialog system is calculated …

Superglue: A stickier benchmark for general-purpose language understanding systems
A Wang, Y Pruksachatkun, N Nangia… – Advances in Neural …, 2019 – papers.nips.cc
Page 1. SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems Alex Wang? New York University Yada Pruksachatkun? New York University Nikita Nangia? New York University Amanpreet …

DeepAssist: Deep Knowledge Grounding for Factual and Conversational Natural Language Interfaces
S Yavuz – 2019 – escholarship.org
… generation human computer interaction technologies through applications like question answering and dialogue systems … However, these models are known to have several problems, especially in the context of chit-chat based dialogue systems: they tend to …

Multimodal dialogue processing for machine translation
A Waibel – The Handbook of Multimodal-Multisensor Interfaces …, 2019 – dl.acm.org
… Field-adaptable and extendable systems. Languages and vocabularies change, and interpreting dialogue systems must evolve alongside such changing languages and vocabularies and adapt to any given dialogue scenario …

Lifecycle of neural semantic parsing
J Cheng – 2019 – era.ed.ac.uk
… convert natural language utterances into machine-understandable logical forms. The technique has a wide range of applications ranging from spoken dialogue systems and natural language interfaces. This thesis focuses on neural network-based semantic parsing …

Improving the Processing of Question Answer Based Legal Documents.
S Chakravarty, M Mehrotra, RVSP Chava, H Liu… – JURIX, 2019 – books.google.com
… This underlines that the Chunking based methods had a good paraphrasing ability that matched the annotated ground truth … J. Williams, A belief tracking challenge task for spoken dialog systems, in: NAACL-HLT Workshop on Future directions and needs in the Spoken Dialog …

Effects of inserting domain vocabulary and fine-tuning BERT for German legal language
CM Yeung – 2019 – essay.utwente.nl
Page 1. Effects of Inserting Domain Vocabulary and Fine-tuning BERT for German Legal Language Master’s Thesis Faculty of Electrical Engineering, Mathematics and Computer Science Masters in Interaction Technology Specialization in Intelligent Systems …

Sparc: Cross-domain semantic parsing in context
T Yu, R Zhang, M Yasunaga, YC Tan, XV Lin… – arXiv preprint arXiv …, 2019 – arxiv.org
… This requires a system developed for SParC to handle information needed over larger databases in different domains. Conversational QA and dialogue system Lan- guage understanding in context is also studied for dialogue and question answering systems …

Learning dense representations for entity retrieval
D Gillick, S Kulkarni, L Lansing, A Presta… – arXiv preprint arXiv …, 2019 – arxiv.org
… well served by random negatives). For ex- ample, negatives mined in this way for paraphrasing or image captioning tasks could actually turn out to be positives that were not explicitly labeled in the data. It is precisely because …

Towards Verified Robustness under Text Deletion Interventions
J Welbl, PS Huang, R Stanforth, S Gowal… – International …, 2019 – openreview.net
… of attack considers word- and character-level perturbation attacks (Ebrahimi et al., 2018; Alzantot et al., 2018) while another type of attack exploits back-translation systems to either mine rules (Ribeiro et al., 2018b) or train syntactically controlled paraphrasing models (Iyyer et al …

A Comprehensive Review of Ethical Frameworks in Natural Language Processing
PF North – 2019 – scss.tcd.ie
… One solution is to rely on manual paraphrasing of language data, a time consuming and expensive process typi- cally performed by a … al (Braunger et al., 2016) observes similar ethical challenges when making use of crowdsourced material for spoken dialog systems in vehicles …

Utilizing Non-Parallel Text for Style Transfer by Making Partial Comparisons.
D Yin, S Huang, XY Dai, J Chen – IJCAI, 2019 – ijcai.org
… The ability to take control over some style attributes (eg sentiment, formality) of the gen- erated text is essential to make language generation systems more intelligent, and is potentially useful in many applica- tions, such as dialogue systems [Niu and Bansal, 2018] and image …

Controllable paraphrase generation with a syntactic exemplar
M Chen, Q Tang, S Wiseman, K Gimpel – arXiv preprint arXiv:1906.00565, 2019 – arxiv.org
… particular types of queries (Kumar et al., 2017). It can also bear on dialogue systems that seek to generate utterances that fit particular functional categories (Ke et al., 2018; Li et al., 2019). To address this task, we propose a …

Reinforcement learning for Dialogue Systems optimization with user adaptation.
N Carrara – 2019 – tel.archives-ouvertes.fr
… The first proposed approach involves clustering of Dialogue Systems (tailored for their respective user) based on their behaviours … The second idea states that before using a dedicated Dialogue System, the first in- teractions with a user should be handled carefully by a safe …

A dynamic speaker model for conversational interactions
H Cheng, H Fang, M Ostendorf – Proceedings of the 2019 Conference of …, 2019 – aclweb.org
Page 1. Proceedings of NAACL-HLT 2019, pages 2772–2785 Minneapolis, Minnesota, June 2 – June 7, 2019. c 2019 Association for Computational Linguistics 2772 A Dynamic Speaker Model for Conversational Interactions …

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
A Korhonen, D Traum, L Màrquez – … of the 57th Annual Meeting of the …, 2019 – aclweb.org
Page 1. ACL 2019 The 57th Annual Meeting of the Association for Computational Linguistics Proceedings of the Conference July 28 – August 2, 2019 Florence, Italy Page 2. Diamond Sponsors: Platinum Sponsors: ii Page 3. Gold sponsors: Keiosk Analytics Silver sponsors …

Text mining in education
R Ferreira?Mello, M André, A Pinheiro… – … : Data Mining and …, 2019 – Wiley Online Library
Abstract The explosive growth of online education environments is generating a massive volume of data, specially in text format from forums, chats, social networks, assessments, essays, among other…

Deep learning for nlp and speech recognition
U Kamath, J Liu, J Whitaker – 2019 – Springer
Page 1. Uday Kamath · John Liu · James Whitaker Deep Learning for NLP and Speech Recognition Page 2. Deep Learning for NLP and Speech Recognition Page 3. Uday Kamath • John Liu • James Whitaker Deep Learning for NLP and Speech Recognition 123 Page 4 …

Computational Framework for Facilitating Intimate Dyadic Communication
D Utami – 2019 – repository.library.northeastern.edu
… In Chapter 4, I introduced the research platform used throughout the experiments in the dissertation, including the Furhat robot and the IrisTK dialog system. In Chapter 5, I answer the first research question by presenting a study on the acceptance …

Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume …
J Burstein, C Doran, T Solorio – Proceedings of the 2019 Conference of …, 2019 – aclweb.org
Page 1. NAACL HLT 2019 The 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies Proceedings of the Conference Vol. 1 (Long and Short Papers) June 2 – June 7, 2019 Page 2 …

Retrieving Relationships from a Knowledge Graph for Question Answering
P Agarwal, M Ramanath, G Shroff – European Conference on Information …, 2019 – Springer
… question-answer pairs. In: Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, EMNLP (2013)Google Scholar. 5. Berant, J., Liang, P.: Semantic parsing via paraphrasing. In: Proceedings of …

Enhancing natural language understanding using meaning representation and deep learning
A Nugaliyadde – 2019 – researchrepository.murdoch.edu.au
Page 1. Enhancing Natural Language Understanding using Meaning Representation and Deep Learning Anupiya Nugaliyadde This thesis is presented for the Degree of Doctor of Philosophy Murdoch University August 2019 Page 2. Page 3. ii Declaration …

Patterns for Expert-Novice Chat
S Höhn – Artificial Companion for Second Language …, 2019 – Springer
Page 1. 3 Patterns for Expert-Novice Chat Abstract This chapter documents the results of the data exploration and provides a bird’s eye perspective on various ways to construct identities of language learners and language experts in instant messaging conversation …

Semantic similarity modeling based on multi-granularity interaction matching
X Li, C Yao, Q Zhang, G Zhang – International Journal of Innovative …, 2019 – ijicic.org
… In the question answering and dialogue system, the user’s input is very casual and colloquial. Paraphrase identification technology can match the user’s questions to the standard questions and improve the recall of answer extraction …

Paraphrase Generation with Collaboration between the Forward and the Backward Decoder
Q Wang, J Ren – … Joint Conference on Neural Networks (IJCNN …, 2019 – ieeexplore.ieee.org
… With this architecture, the forward decoder can exploit two kinds of contextual information. Because of using future hidden state information bt, it is able to alleviate the semantic error while paraphrasing the source text. IJCNN 2019 …

A Question Answering and Quiz Generation Chatbot for Education
AS Sreelakshmi, SB Abhinaya, A Nair… – 2019 Grace Hopper …, 2019 – ieeexplore.ieee.org
… Techniques such as ex- tractive summarization, sentence splitting, fusion and com- pression, paraphrasing, and textual entailment may be used … [22] Zhou, H., Huang, M. (2016, December). Context-aware natural lan- guage generation for spoken dialogue systems …

Self-Attentional Models Application in Task-Oriented Dialogue Generation Systems
M Saffar Mehrjardi – 2019 – era.library.ualberta.ca
Page 1. Self-Attentional Models Application in Task-Oriented Dialogue Generation Systems by Mansour Saffar Mehrjardi A thesis submitted in partial fulfillment of the requirements for the degree of Master of Science Department of Computing Science University of Alberta …

Text Summarization for Chatbots
M Lustig – 2019 – support.dce.felk.cvut.cz
… Both approaches can however be combined. For example, the navigation between states of an automaton in the frame based dialogue system can be based on learned probabilities. The area of dialogue systems development resembles more an alchemy than a strict science …

Learning Dense Representations for Entity Retrieval
D Gillick, S Kulkarni, L Lansing, A Presta, J Baldridge… – 2019 – research.google
… well served by random negatives). For ex- ample, negatives mined in this way for paraphrasing or image captioning tasks could actually turn out to be positives that were not explicitly labeled in the data. It is precisely because …

Goal Oriented and Open Domain Dialogue Management
M Vodolán – 2019 – dspace.cuni.cz
… In the second part, we address our objectives towards providing a principal so- lution to open domain dialogue systems. We start by describing the typical challenges the open domain dialogue system has to deal with and discuss usual approaches in Chapter 7. We propose …

Feature Engineering and Ensemble-Based Approach for Improving Automatic Short-Answer Grading Performance
A Sahu, PK Bhowmick – IEEE Transactions on Learning …, 2019 – ieeexplore.ieee.org
… The updating technique is similar to the pseudo-relevance feedback used in information retrieval [29]. This leads to enhancement of vocabulary of the model answer due to the paraphrasing observed across the student answers …

The state of nlp literature: A diachronic analysis of the acl anthology
SM Mohammad – arXiv preprint arXiv:1911.03562, 2019 – arxiv.org
… and Italian. FFA percentages are also relatively higher for certain areas of NLP such as work on prosody, readability, discourse, dialogue, paraphrasing, and individual parts of speech such as adjectives and verbs. FFA percentages …

Machine reading comprehension: a literature review
X Zhang, A Yang, S Li, Y Wang – arXiv preprint arXiv:1907.01686, 2019 – arxiv.org
… Thus, this corpus encourages the use of world knowledge in comparison with CNN/Daily Mail, and therefore focuses less on paraphrasing parts of a context … 32.7 39.8 Paraphrasing Q: Who is the struggle between in Rwanda …

Humour-in-the-loop: Improvised Theatre with Interactive Machine Learning Systems
KW Mathewson – 2019 – era.library.ualberta.ca
… create a narrative. This thesis aims to test and evaluate novel dialogue system improvements by through experimentation with improvisational theatre performers and au- diences … tions between humans and artificial-intelligence-powered dialogue systems. To …

Learning natural language interfaces with neural models
L Dong – 2019 – era.ed.ac.uk
… 68 4.5.3 Results . . . . . 69 4.6 Summary . . . . . 75 5 Query Paraphrasing 77 5.1 RelatedWork . . . . . 79 5.2 ProblemFormulation . . . . . 80 5.2.1 ParaphraseGeneration …

A comparative survey of recent natural language interfaces for databases
K Affolter, K Stockinger, A Bernstein – The VLDB Journal, 2019 – Springer
Over the last few years, natural language interfaces (NLI) for databases have gained significant traction both in academia and industry. These systems use very different approaches as described in…

Unsupervised Text Representation Learning with Interactive Language
H Cheng – 2019 – digital.lib.washington.edu
… Some recent work on the interactive model includes neural conversational models [34, 35] and neural-based spoken dialogue systems [36, 37] … Page 24. 13 tion scenario takes place between a human user and a dialogue system powered by conversational …

Implementation and evaluation of a shopping assistance chatbot in an e-commerce case
T Böger – 2019 – run.unl.pt
… retrieval from a knowledge base, true machine translation, or a dialogue system (Chowdhury, 2005; Dahl … the intent behind an utterance while NLP focusses on paraphrasing and thus … With ELIZA Weizenbaum (1966) set the foundation for interactive dialogue systems and the …

Neural Network Models for Text Understanding
L Zhang – 2019 – utd-ir.tdl.org
… texts, and (3) make inference from the texts to generate solutions for high-level tasks, such as Semantic Relation Extraction, Textual Entailment, Semantic Textual Similarity, Sentiment Analysis, Dialog Systems, Question Answering (QA) etc. This problem has been tradition …

Cooperation in online conversations: the response times as a window into the cognition of language processing
B Jacquet, J Baratgin, F Jamet – Frontiers in psychology, 2019 – frontiersin.org
Measuring the cognitive cost of interpreting the meaning of sentences in a conversation is a complex task, but it is also at the core of Sperber and Wilson’s Relevance Theory. In cognitive sciences, the delay between a stimulus and its response is often used as an approximation of …

Co-designing a chatbot for and with refugees and migrants
Z Chen – 2019 – aaltodoc.aalto.fi
… process and analyze large amounts of natural language data. ³A component of a dialog system, responsible for the state and flow of the conversation. Page 16. 4 1.2 Motivation This thesis developed out of my great empathy …

Generating textual adversarial examples for deep learning models: A survey
WE Zhang, QZ Sheng, AAF Alhazmi, C Li – arXiv preprint arXiv …, 2019 – deepai.org
01/21/19 – With the development of high computational devices, deep neural networks (DNNs), in recent years, have gained significant populari…

Explanation in artificial intelligence: Insights from the social sciences
T Miller – Artificial Intelligence, 2019 – Elsevier
… The very experts who understand decision-making models the best are not in the right position to judge the usefulness of explanations to lay users — a phenomenon that Miller et al. refer to (paraphrasing Cooper [132], [31]) as “the inmates running the asylum” …

Towards the Automatic Classification of Student Answers to Open-ended Questions
JG Alvarado Mantecon – 2019 – ruor.uottawa.ca
… learning algorithm to learn the cost of a bigger set of edit operations (eg stemming match, synonym alignment, number of word shifts, insertion, deletion, phrasal paraphrasing, substitution) to calculate a similarity measure between two sentences …

DysTexia: An Assistive System for People with Dyslexia
T PA?ILOVÁ – 2019 – is.muni.cz
Page 1. Page 2. Page 3. You all know how much you mean to me. No words needed… Page 4. Declaration Hereby I declare that this paper is my original authorial work, which I have worked out on my own. All sources, references …

A narrative sentence planner and structurer for domain independent, parameterizable storytelling
SM Lukin, MA Walker – Dialogue & Discourse, 2019 – firstmonday.org
… Natural Language and Dialogue Systems Lab University of California, Santa Cruz, CA … Aggregation is inclusive of aspects of abstractive text summarization, with parallels in sentence compression, fusion, lexical paraphrasing, and reorganization by reducing syntactic structures …

Learning an executable neural semantic parser
J Cheng, S Reddy, V Saraswat, M Lapata – Computational Linguistics, 2019 – MIT Press
Create a new account. Email. Returning user. Can’t sign in? Forgot your password? Enter your email address below and we will send you the reset instructions. Email. Cancel. If the address matches an existing account you will …

Understanding the interplay between technology and social ties in later life
S Nikitina – 2019 – iris.unitn.it
Page 1. Understanding the interplay between technology and social ties in later life: How social ties promote use of technology and how technology can promote social relationships Svetlana Nikitina Advisor partner University: Prof. Fabio Casati Advisor home University: Prof …

Automated Essay Scoring: Argument Persuasiveness
Z Ke – 2019 – utd-ir.tdl.org
Page 1. AUTOMATED ESSAY SCORING: ARGUMENT PERSUASIVENESS by Zixuan Ke APPROVED BY SUPERVISORY COMMITTEE: Vincent Ng, Chair Nicholas Ruozzi Sriraam Natarajan Page 2. Copyright 2019 Zixuan Ke All Rights Reserved Page 3. This Master’s thesis …

Unsupervised summarization of public talk radio
S O’Brien – 2019 – dspace.mit.edu
… levels of noise such as music, advertisements, and traffic and weather announcements. Despite significant efforts to develop spoken dialogue systems, colloquial speech summarization of transcribed text remains an open problem. This may be due to …

Cut & recombine: reuse of robot action components based on simple language instructions
MJ Aein, A Haidu, D Chrysostomou, B Ridge… – … , 2019, Vol. 38, iss. 10-11, 2019 – vdu.lt
Page 1. Article The International Journal of Robotics Research 2019, Vol. 38(10-11) 1179–1207 © The Author(s) 2019 Article reuse guidelines: sagepub.com/journals- permissions DOI: 10.1177/0278364919865594 journals.sagepub.com/home/ijr …

Profiling Artificial Intelligence as a Material for User Experience Design
Q Yang – 2019 – reports-archive.adm.cs.cmu.edu
Page 1. Pro ling Arti cial Intelligence as a Material for User Experience Design Qian Yang CMU HCII 20 100 July 2020 Human-Computer Interaction Institute School of Computer Science Carnegie Mellon University Pittsburgh, PA 15213 …

Advances in Information Retrieval: 41st European Conference on IR Research, ECIR 2019, Cologne, Germany, April 14–18, 2019, Proceedings, Part I
L Azzopardi, B Stein, N Fuhr, P Mayr, C Hauff… – 2019 – books.google.com
Page 1. Leif Azzopardi· Benno Stein · Norbert Fuhr· Philipp Mayr· Claudia Hauff· Djoerd Hiemstra (Eds.) Advances in Information Retrieval 41st European Conference on IR Research, ECIR 2019 Cologne, Germany, April 14–18, 2019 Proceedings, Part I 123 Page 2 …

(Visited 673 times, 1 visits today)