Paraphrasing & Dialog Systems 2017


Notes:

  • Script understanding system

Resources:

Wikipedia:

References:

See also:

Paraphrase DatabaseSPG (Statistical Paraphrase Generation)


Data-driven dialogue systems for social agents
KK Bowden, S Oraby, A Misra, J Wu, S Lukin – arXiv preprint arXiv …, 2017 – arxiv.org
… for language understanding from open domain conversations, and many corpora are available for building data-driven dialogue systems [17, 18] … data-driven retrieval with modules for sentiment analy- sis and style, topic analysis, summarization, paraphrasing, and rephrasing …

Relevance of unsupervised metrics in task-oriented dialogue for evaluating natural language generation
S Sharma, LE Asri, H Schulz, J Zumer – arXiv preprint arXiv:1706.09799, 2017 – arxiv.org
… Even today, many task-oriented dialogue systems deployed in production are rule-based and template-based … In the past, Oh and Rudnicky (2000) proposed a corpus-based approach for Natural Language Gen- eration (NLG) for task-oriented dialogue systems …

Sequential Dialogue Context Modeling for Spoken Language Understanding
A Bapna, G Tur, D Hakkani-Tur, L Heck – Proceedings of the 18th …, 2017 – aclweb.org
… The goal of the spoken language understanding module of our dialogue system is to map each user utterance into frame based semantics … ated interactions were then translated to their nat- ural language counterparts and sent out to crowd- workers for paraphrasing into natural …

Ethical Challenges in Data-Driven Dialogue Systems
P Henderson, K Sinha, N Angelard-Gontier… – arXiv preprint arXiv …, 2017 – arxiv.org
… two kinds of input noise for adversarial ex- amples for end-to-end conversational models: (1) misspelled words in dialogue systems, where we … As shown in Table 3, paraphrasing and mis- spellings of a single character can cause significant changes in semantic meaning and …

Acquisition and Assessment of Semantic Content for the Generation of Elaborateness and Indirectness in Spoken Dialogue Systems
L Pragst, K Yoshino, W Minker, S Nakamura… – Proceedings of the …, 2017 – aclweb.org
… Acquisition and Assessment of Semantic Content for the Generation of Elaborateness and Indirectness in Spoken Dialogue Systems … Abstract In a dialogue system, the dialogue man- ager selects one of several system actions and thereby determines the system’s be- haviour …

Research Problems in Natural Language Processing–A brief Overview
P Selvaperumal – 2017 – ijsrset.com
… chair. Thus use of POS tagging to improve performance of a search engine or other NLP systems like dialogue system, question and answering system is attractive … passage. Text paraphrasing is another enticing are to work on …

Context Respectful Counseling Agent integrated with Robot nodding for Dialog Promotion
K Kurashige, E Sakurai, R Knauf, S Tsuruta, Y Sakurai… – pdfs.semanticscholar.org
… Simple paraphrasing Natural language dialog processing Context- respectful reasoning response User … 258-268, 2010. [7] S. Han, K. Lee, D. Lee, GG Lee, “Counseling Dialog System with 5W1H Extraction” Proceeding of the SIGDIAL 2013 Conferrence, pp. 349-353, 2013 …

Improving Frame Semantic Parsing with Hierarchical Dialogue Encoders
A Bapna, G Túr, D Hakkani-Túr, L Heck – arXiv preprint arXiv:1705.03455, 2017 – arxiv.org
… The goal of the conversational language under- standing module of our dialogue system is to map each user utterance into frame based … These generated interactions were then translated to their natural language counterparts and sent out to crowd-workers for paraphrasing …

Automatic generation of plot for education by teacher-student dialogue style
H Ito, Y Asano, M Yoshikawa – … of the 2017 International Conference on …, 2017 – dl.acm.org
… With Nadamoto method, exaggeration, back- channeling question-and-answers and paraphrasing are used for generating dialogue … In SIG-KSN-015-03. [8] Otake, Y., and Hagiwara M. 2012. A dialogue system for the elderly considering utterance intention …

How Would You Say It? Eliciting Lexically Diverse Dialogue for Supervised Semantic Parsing
A Ravichander, T Manzini, M Grabmair… – Proceedings of the 18th …, 2017 – aclweb.org
… Supervised semantic parsing is of special practical interest as while trying to build dialogue systems for new domains, it is important to be able to … As the authors of (Wang et al., 2015) point out, paraphrasing overcomes this overhead by being a considerably lightweight form of …

Collection of responsive utterances to show attentive hearing attitude to speakers
T Ohno, M Murata, S Matsubara – Proceedings of the 11th International …, 2017 – dl.acm.org
… fixed expressions which can be classified based on the literature [6] and the remaining 9.66% were non-fixed ex- pressions such as echoic response, paraphrasing and complement … Dialogue system characterisation by back-channelling patterns extracted from dialogue corpus …

The Extended SPaRKy Restaurant Corpus: designing a corpus with variable information density
DM Howcroft, D Klakow, V Demberg… – Proc. Interspeech …, 2017 – isca-speech.org
… We introduce a new corpus in the restaurant recommen- dation and comparison domain, collected in a paraphrasing paradigm, where subjects wrote … for a wider range of applications, users, and us- age situations, we need to develop NLG and dialogue systems which exhibit a …

Effective Paraphrase Expansion in Addressing Lexical Variability
V Konovalov, M Adler, I Dagan – fruct.org
… and lexical semantics to improve the accuracy and the robustness of supervised models in situated dialogue systems” in Conference on … argument structure using lexico-grammatical resources,” in Proceedings of the second inter- national workshop on Paraphrasing-Volume 16 …

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
… It contains recordings of Dutch children, non-natives, and the elderly interacting with a spoken dialogue system … syllable lengthening (VER), self-talk (SLF), shouting (SCH), repetition of the system prompt, repetition of the user utterance, accent shift, paraphrasing, restart (RES …

A Chatbot for Psychiatric Counseling in Mental Healthcare Service Based on Emotional Dialogue Analysis and Sentence Generation
KJ Oh, D Lee, B Ko, HJ Choi – Mobile Data Management (MDM …, 2017 – ieeexplore.ieee.org
… In the chatbot, method for paraphrasing the various representative expressions applies to understand by the machine using analysis of sentence … Based on the information, the purpose of the service is to develop a personalized dialog system that communicate emotionally with …

Understanding Task Design Trade-offs in Crowdsourced Paraphrase Collection
Y Jiang, JK Kummerfeld, WS Laseck – arXiv preprint arXiv:1704.05753, 2017 – arxiv.org
… Mark Dras. 1999. Tree adjoining grammar and the reluctant paraphrasing of text. Ph.D. the- sis, Macquarie University NSW 2109 Australia … 2014. Crowdsourcing language genera- tion templates for dialogue systems. In Proc. of the INLG and SIGDIAL 2014 Joint Session …

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
… In addition, it enables a trusted master to teach it new question-answer pairs via question-answer paraphrasing, and solicits help … robots Pepper and NAO, and the telepresence robot known as Double from Double Robotics[4]. Keywords Spoken dialog systems; text classification …

Response selection from unstructured documents for human-computer conversation systems
Z Yan, N Duan, J Bao, P Chen, M Zhou, Z Li – Knowledge-Based Systems, 2017 – Elsevier
This paper studies response selection for human-computer conversation systems. Existing retrieval-based human-computer conversation systems are intended to repl.

How Would You Say It? Eliciting Lexically Diverse Data For Supervised Semantic Parsing
A Ravichander, T Manzini, M Grabmair, G Neubig… – nzini.com
… Supervised semantic parsing is of special practical interest as while trying to build dialogue systems for new domains, it is important to be able to … As the authors of (Wang et al., 2015) point out, paraphrasing overcomes this overhead by being a considerably lightweight form of …

Building CMU Magnus from User Feedback
S Prabhumoye, F Botros, K Chandu… – Alexa Prize …, 2017 – nzini.com
… the following sections we discuss the structure of our dataset, the strategies we followed to use this data in a dialogue system and present … We generate a representation of both the test query and the paraphrasing using a bidirectional-LSTM and use the loss function as specified …

The Dense Use of Lexicalization in Dialogues by EFL Students at Jordan University-Aqaba
AH Al-Awabdeh, IB Abdo – Education, 2017 – file.scirp.org
… This study gives some insights, observations, and elaborations of the implications for spoken dialogue systems at discourse level (Henry, 2006) … and complex lexical repetition were the highest percentages of occur- rence The complex types (complex paraphrasing, co-reference …

Exploring neural text simplification models
S Nisioi, S Štajner, SP Ponzetto, LP Dinu – … of the 55th Annual Meeting of …, 2017 – aclweb.org
… Build- ing end-to-end dialogue systems using generative hi- erarchical neural network models … century, gingerbread was brought to Swe- den by German immigrants.” and “German immigrants brought it to Sweden during the 13th century.” Full lexical paraphrasing “During the …

From Shakespeare to Twitter: What are Language Styles all about?
W Xu – Proceedings of the Workshop on Stylistic Variation, 2017 – aclweb.org
… I think the answer is yes, and the twin research topics of paraphrasing and seman- tic similarity could be part of the solution as many language … Another subsequent challenge is how to transfer the subtle style differences into natural language generation and dialog systems …

From Pragmatics to Dialogue
I Kecskes – The Routledge Handbook of Language and Dialogue, 2017 – books.google.com
… is computational pragmatics that focuses on the application of pragmatics to dialogue modelling, especially the development of spoken dialogue systems intended to interact … If this is not clear from their utterance they try to reinforce it with repetition, paraphrasing or other means …

Proceedings of the 2nd Workshop on Representation Learning for NLP
P Blunsom, A Bordes, K Cho, S Cohen, C Dyer… – Proceedings of the 2nd …, 2017 – aclweb.org
… A Frame Tracking Model for Memory-Enhanced Dialogue Systems Hannes Schulz, Jeremie Zumer, Layla El Asri and Shikhar Sharma … In the first part of the talk I will revisit bilingual pivoting in the context of neural machine translation and present a paraphrasing model based …

Unsupervised Automatic Text Style Transfer Using LSTM
M Han, O Wu, Z Niu – National CCF Conference on Natural Language …, 2017 – Springer
… increasingly popular with its applications to various NLP tasks, such as machine translation [1], speech recognition [18], and dialogue systems [27] producing … Studies such as [13, 25] were among the first to introduce the Seq2Seq model [1] directly to the task of paraphrasing …

A data-driven model of explanations for a chatbot that helps to practice conversation in a foreign language
S Höhn – Proceedings of the 18th Annual SIGdial Meeting on …, 2017 – aclweb.org
… The the study contributes to language understanding for dialogue systems tar- geting language learners and has implications for user and … of the trouble source and the repair initiation for- mat and include confirmations / disconfirmations, definition work and paraphrasing of the …

Boosting a Rule-Based Chatbot Using Statistics and User Satisfaction Ratings
O Efraim, V Maraev, J Rodrigues – Conference on Artificial Intelligence …, 2017 – Springer
… arXiv preprint arXiv:1603.08023 (2016). 19. Lowe, R., Serban, IV, Noseworthy, M., Charlin, L., Pineau, J.: On the evaluation of dialogue systems with next utterance classification … In: Proceedings of the ACL-PASCAL Workshop on Textual Entailment and Paraphrasing, pp. 42–47 …

Ask Me Otherwise: Synonym-Based Memory Networks for Reading Comprehension
B Srivatsan – bharathsrivatsan.com
… One is the subdomain of paraphrasing, which essentially focuses on training machines to identify or 3 A popularly used dataset in this space Page 9 … Berant and Liang [17] build two paraphrasing models: an associative approach and a vector-space approach, and train them on …

Semantic specialisation of distributional word vector spaces using monolingual and cross-lingual constraints
N Mrkši?, I Vuli?, DÓ Séaghdha, I Leviant… – arXiv preprint arXiv …, 2017 – arxiv.org
… To the best of our knowledge, this is the first work on multilingual training of any compo- nent of a statistical dialogue system … (2015) modify the skip-gram objective function to fine-tune word vectors by injecting paraphrasing con- straints from PPDB. Mrkšic et al …

Soft Seeded SSL Graphs for Unsupervised Semantic Similarity-based Retrieval
A Srivastava, M Datt – Proceedings of the 2017 ACM on Conference on …, 2017 – dl.acm.org
… 1 INTRODUCTION Semantic matching and ranking play a key role in various informa- tion retrieval and natural language understanding applications such as modern web search, dialogue systems, cross language informa- tion retrieval, paraphrasing, textual entailment …

Parsing natural language conversations using contextual cues
S Srivastava, A Azaria, T Mitchell – Proceedings of the 26th …, 2017 – azariaa.com
… hand, a notable application area that has ex- plored conversational context within highly specific settings is state tracking in dialog systems … of the heuris- tics proposed in this paper for improving parsing performance are motivated by previous work on paraphrasing for semantic …

Continuous Learning as a Service for Conversational Virtual Agents
S Agarwal, S Atreja, G Dasgupta – International Conference on Service …, 2017 – Springer
… In addition, paraphrasing is performed using LSTM [9] (out of scope of this paper) … Particularly for dialog systems and conversation agents, [16, 19] exploited a combination of active and semi-supervised learning approach for better training …

Redundancy localization for the conversationalization of unstructured responses
S Krause, M Kozhevnikov, E Malmi… – Proceedings of the 18th …, 2017 – aclweb.org
… agents. Several strands of dialogue systems have emerged which differ in underlying goals and methods … 6. 3Among other things, to accurately identify redundancy the model needs to have at least some notion of paraphrasing. The …

Why We Need New Evaluation Metrics for NLG
J Novikova, O Dušek, AC Curry, V Rieser – arXiv preprint arXiv …, 2017 – arxiv.org
… This is rarely the case, as shown by various studies in NLG (Stent et al., 2005; Belz and Reiter, 2006; Reiter and Belz, 2009), as well as in related fields, such as dialogue systems (Liu et al., 2016), machine translation (MT) (Callison-Burch et al., 2006), and image captioning …

Measuring Synchrony in Task-based Dialogues
J Reverdy, C Vogel – Proc. Interspeech 2017, 2017 – pdfs.semanticscholar.org
… Repetitions of lex- emes can be viewed as midway between a scale that goes from exact same word to paraphrasing an idea … with the method are encouraging as it could be potentially used in a predictive machine learning task in the perspective of a use in dialogue systems …

SCI-FII: Speculative Conversational Interface Framework for Incremental Inference on Modularized Services
J Lee, I Hwang, T Hubregtsen… – … (MDM), 2017 18th …, 2017 – ieeexplore.ieee.org
… Fig. 1 (b) shows the timing diagram of a dialog system 279 Page 3. Fig … In a roll-forward method, the dialog system may employ a pool of multiple instances holding the state of the conversation progress, and keep the history of inputs for the stage …

Revisiting the ISO standard for dialogue act annotation
H Bunt, V Petukhova, AC Fang – Proceedings of the 13th Joint ISO-ACL …, 2017 – aclweb.org
… Alex Fang Dialogue Systems Group City University of Hong Kong alex.fang@cityu. edu.hk Abstract … Feedback at the level of understanding can be expressed for example by “I see” or by paraphrasing something that was expressed …

Domain-Adaptable Hybrid Generation of RDF Entity Descriptions
O Biran, K McKeown – Proceedings of the Eighth International Joint …, 2017 – aclweb.org
… known from the RDF onto- logy). The paraphrasing approach uses sentence- level vector representations to calculate the simi- larity of the template to all of the existing lexica- lizations of an STT. If the template is determined …

Questions, pictures, answers
M Theune, B van Schooten, R Op den Akker, W Bosma… – pure.uvt.nl
… A dialogue system might react by (further) extending the answer so that the correctness can be verified appropriately, see section 3.1 … is a difficult type of question to handle properly, but might simply be answered by producing a suitable figure caption paraphrasing the entire …

Multimodal breathiness in interaction: from breathy voice quality to global breathy “body behavior quality”
L Tsvetanova, V Aubergé, Y Sasa – 2017 – pdfs.semanticscholar.org
… the elderly’s vocal and non-vocal behavior changes gradually throughout the experiment by varying in breathiness, commands paraphrasing, and non … The first works in this direction have been implemented in the robot’s dialog system called SARSI (Socio- Affective Robotics …

Controlling linguistic style aspects in neural language generation
J Ficler, Y Goldberg – arXiv preprint arXiv:1707.02633, 2017 – arxiv.org
Page 1. Accepted as a long paper in Stylistic Variation Workshop 2017 Controlling Linguistic Style Aspects in Neural Language Generation Jessica Ficler and Yoav Goldberg Computer Science Department Bar-Ilan University Israel {jessica.ficler, yoav.goldberg}@gmail.com …

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 … Recent work on applying neural network to paraphrasing show similar architectures outperforms LSTM-based architectures [21] for short …

Predicting emotional word ratings using distributional representations and signed clustering
J Sedoc, D Preo?iuc-Pietro, L Ungar – … of the 15th Conference of the …, 2017 – aclweb.org
… Inferring the emotional content of words is important for text-based sentiment anal- ysis, dialogue systems and psycholinguis- tics, but word ratings are expensive to collect at scale and across languages or … 2016. Discovering User Attribute Stylistic Differences via Paraphrasing …

Classification-based spoken text selection for LVCSR language modeling
V Chunwijitra, C Wutiwiwatchai – EURASIP …, 2017 – asmp-eurasipjournals.springeropen …
… (3) A sentence starts with a topic-comment structure [34]. (3) A sentence starts with a subject-predicate form [34]. (4) Repetition, word duplication or paraphrasing, often appears [35]. (4) A sentence contains less repetition [35] …

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 …

Recent trends in deep learning based natural language processing
T Young, D Hazarika, S Poria, E Cambria – arXiv preprint arXiv …, 2017 – arxiv.org
… White, 2014). NLP enables computers to perform a wide range of natural language related tasks at all levels, ranging from parsing and part-of-speech (POS) tagging, to machine translation and dialog systems. Deep learning …

Inference is Everything: Recasting Semantic Resources into a Unified Evaluation Framework
AS White, P Rastogi, K Duh, B Van Durme – Proceedings of the Eighth …, 2017 – aclweb.org
… of a new RTE model on the SNLI dataset, but this black-box evaluation does not help us understand the fine-grained aspects of a model’s capability in performing particular types of natural language inference, such as its ability to handle coreference, paraphrasing, or its ability …

A Robotic Couples Counselor for Promoting Positive Communication
D Utami, TW Bickmore, LJ Kruger – relationalagents.com
… Turn-taking is regulated by selecting the next speaker using both robot gaze and speech-based reference to users’ given names (programmed into the dialogue system prior to the start of the … Any of the following: 1) Paraphrasing (the listener repeated back what the speaker said …

Automatic Neural Question Generation using Community-based Question Answering Systems
T Baghaee – 2017 – uleth.ca
Page 1. AUTOMATIC NEURAL QUESTION GENERATION USING COMMUNITY- BASED QUESTION ANSWERING SYSTEMS TINA BAGHAEE Bachelor of Science, Shahid Beheshti University, 2011 A Thesis Submitted to the …

Hybrid Deep Open-Domain Question Answering
A Aghaebrahimian – ufal.mff.cuni.cz
… Cloze-type QA provides a dependable measure for MC. However, in QA systems for other pur- poses like in dialogue systems or scientist’s as- sistants, the answers are not known in advance. It is assumed that they are available somewhere on the Internet …

Multi-level mining and visualization of scientific text collections
P Accuosto, F Ronzano, D Ferrés, H Saggion – 2017 – repositori.upf.edu
… entities paraphrasing paraphrase paraphrases noun paraphrasing pairs subject object compound pair entailment knowledge … words dialogue systems user dialogue system information models model items speech goals interaction web …

Multi-level mining and visualization of scientific text collections: Exploring a bi-lingual scientific repository
P Accuosto, F Ronzano, D Ferrés… – Proceedings of the 6th …, 2017 – dl.acm.org
… entities paraphrasing paraphrase paraphrases noun paraphrasing pairs subject object compound pair entailment knowledge … words dialogue systems user dialogue system information models model items speech goals interaction web …

Discovering Stylistic Variations in Distributional Vector Space Models via Lexical Paraphrases
X Niu, M Carpuat – Proceedings of the Workshop on Stylistic Variation, 2017 – aclweb.org
… are deployed in a variety of settings, detecting and analyzing stylistic variations is becoming increas- ingly important, and is relevant to applications ranging from dialogue systems (Mairesse, 2008 … (2012) used a machine translation model to paraphrasing Shakespeares plays …

Chatbot for Laundry and Dry Cleaning Service
BJ K?íž – is.muni.cz
Page 1. Masaryk University Faculty of Informatics Chatbot for Laundry and Dry Cleaning Service Master’s Thesis Bc. Jakub K?íž Brno, Spring 2017 Page 2. Masaryk University Faculty of Informatics Chatbot for Laundry and Dry Cleaning Service Master’s Thesis Bc. Jakub K?íž …

Interpretable semantic textual similarity: Finding and explaining differences between sentences
I Lopez-Gazpio, M Maritxalar, A Gonzalez-Agirre… – Knowledge-Based …, 2017 – Elsevier
… return a similarity score. STS is related to both paraphrasing and textual entailment, but instead of being binary it reflects a graded notion. It also differs from textual entailment in that it is not directional [13,27]. STS is an enabling …

Building Natural Language Interfaces to Web APIs
Y Su, AH Awadallah, M Khabsa, P Pantel… – Proceedings of the …, 2017 – dl.acm.org
Page 1. Building Natural Language Interfaces to Web APIs Yu Su1, Ahmed Hassan Awadallah2, Madian Khabsa2 Patrick Pantel2, Michael Gamon2, Mark Encarnacion2 1University of California, Santa Barbara, 2Microsoft Research …

Natural Logic Inference for Emotion Detection
H Ren, Y Ren, X Li, W Feng, M Liu – Chinese Computational Linguistics …, 2017 – Springer
… research topics in natural language processing, emotion detection is widely used in opinion mining, product recommendation, dialog system, and so … 7 Workshop, Tokyo, Japan (2008)Google Scholar. 8. Androutsopoulos, I., Malakasiotis, P.: A survey of paraphrasing and textul …

Defining Soldier Intent in a Human-Robot Natural Language Interaction Context
E Holder – 2017 – dtic.mil
Page 1. ARL-TR-8195 ? OCT 2017 US Army Research Laboratory Defining “Soldier Intent” in a Human–Robot Natural Language Interaction Context by Eric Holder Approved for public release; distribution is unlimited. Page 2. NOTICES Disclaimers …

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 …

Abstractive Document Summarization via Neural Model with Joint Attention
L Hou, P Hu, C Bei – National CCF Conference on Natural Language …, 2017 – Springer
… are expected to have more chance to generate better summaries by using more flexible expressions such as paraphrasing, compression or … framework is the fundamental for many current NLP models and is widely used in machine translation, dialog systems and automatic …

Learning Algorithms for Broad-Coverage Semantic Parsing
S Swayamdipta – 2017 – cs.cmu.edu
… Page 2. Abstract Broad-coverage semantics holds great potential for improving a variety of downstream applications, such as question-answering, relation extraction, and paraphrasing … 22 5.2 Semantically-Motivated Query Paraphrasing …

Constructing Sentences from Text Fragments: Aggregation in Text-to-text Generation
V Chenal – 2017 – digitool.library.mcgill.ca
… example; • automatic text correction: correcting spelling and grammar errors; • automatic paraphrasing. In particular, automatic summarization has been studied extensively and a large body of literature on this subject, too large to survey here, exists …

Natural Language Inference with External Knowledge
Q Chen, X Zhu, ZH Ling, D Inkpen – arXiv preprint arXiv:1711.04289, 2017 – arxiv.org
… 2 Page 3. 2016), and dialogue system (Chen et al., 2016) … Bill MacCartney and Christopher D Manning. Natural logic for textual inference. In Proceedings of the ACL-PASCAL Workshop on Textual Entailment and Paraphrasing, pp. 193–200, 2007 …

Grounding proposition stores for question answering over linked data
B Cabaleiro, A Peñas, S Manandhar – Knowledge-Based Systems, 2017 – Elsevier
… More recent work aims to alleviate the supervision problem by using forms of distant supervision, ie observation of system behaviour [11], conversations from dialog systems [12], schema matching [13], questions [5] and question-answer pairs [14–18] …

Learning an Executable Neural Semantic Parser
J Cheng, S Reddy, V Saraswat, M Lapata – arXiv preprint arXiv …, 2017 – arxiv.org
Page 1. arXiv:1711.05066v1 [cs.CL] 14 Nov 2017 Learning an Executable Neural Semantic Parser Jianpeng Cheng University of Edinburgh Siva Reddy Stanford University Vijay Saraswat IBM TJ Watson Research Mirella Lapata University of Edinburgh …

A Complete Bibliography of ACM Transactions on Asian Language Information Processing
NHF Beebe – 2017 – tug.ctan.org
… Paragraphs [202]. parallel [85]. Paraphrasing [210]. Parsed [136] … [37] Harksoo Kim and Jungyun Seo. Resolution of referring expressions in a Korean multimodal dialogue system. ACM Transactions on Asian Lan- guage Information Processing, 2(4):324–337, December 2003 …

Text Generation Using Different Recurrent Neural Networks
P Taneja, KG Verma – 2017 – dspace.thapar.edu
… Then, the decoder generates words of the headline ending with an end-of-sequence symbol using a softmax layer. The model is found to be quite effective at concisely paraphrasing news articles. The encoder-decoder architecture is shown in figure 2.2. Page 26. 15 …

Finding enthymemes in real-world texts: A feasibility study
O Razuvayevskaya, S Teufel – Argument & Computation, 2017 – content.iospress.com
… It often comprises a set of procedures, such as paraphrasing, reformulation, and insertion of generally accepted facts … [2]. E. Black and A. Hunter, Using enthymemes in an inquiry dialogue system, International Foundation for Autonomous Agents and Multiagent Systems 1: ((2008 …

Deep Reinforcement Learning in Natural Language Scenarios
J He – 2017 – digital.lib.washington.edu
… Many artificial intelligence tasks involve sequential decision making and delayed rewards, such as video gaming, human-computer dialogue systems, newsfeed recommendation, and … computer or human-robot dialog systems, the agent needs to understand the dialog state …

Explanation in artificial intelligence: Insights from the social sciences
T Miller – arXiv preprint arXiv:1706.07269, 2017 – arxiv.org
… 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 [17]) as “the inmates running the asylum” …

Abstractive document summarization with a graph-based attentional neural model
J Tan, X Wan, J Xiao – Proceedings of the 55th Annual Meeting of the …, 2017 – aclweb.org
… It involves multiple subproblems like simplifica- tion, paraphrasing, and fusion … We adopt an encoder-decoder framework, which is 1172 Page 3. widely used in machine translation (Bahdanau et al., 2014) and dialog systems (Mou et al., 2016), etc …

Propositional Knowledge: Acquisition and Application to Syntactic and Semantic Parsing
B Cabaleiro Barciela – 2017 – e-spacio.uned.es
Page 1. Thesis for the Degree of Doctor of Philosophy 2017 Propositional Knowledge: Acquisition and Application to Syntactic and Semantic Parsing Bernardo Cabaleiro Barciela University Master’s Degree in Languages and Computer Systems (National Distance Education …

Modeling common sense knowledge via scripts
A Modi – 2017 – publikationen.sulb.uni-saarland.de
… To model script knowledge, three main tasks need to be addressed: event order- ing, event paraphrasing and event prediction. This dissertation introduces a novel … In addition to event ordering and paraphrasing, a script understanding system should …

College of Natural Science
A Gebremariam – 2017 – etd.aau.edu.et
… human about arbitrary topics and the goal of research in NLP and in natural language understanding, and in dialogue system in particular is to break down the barrier [4]. Many researches been conducted on topics related to the application of natural language processing …

Thesis Material-Rasmus Dall
R Dall – 2017 – datashare.is.ed.ac.uk
Page 1. Statistical Parametric Speech Synthesis Using Conversational Data and Phenomena Rasmus Dall T H E U NIVER S I T Y O F E DI NBU R G H Doctor of Philosophy Institute for Language, Cognition and Computation School of Informatics University of Edinburgh 2017 …

Methods and Techniques for Clinical Text Modeling and Analytics
Y Ling – 2017 – search.proquest.com
Methods and Techniques for Clinical Text Modeling and Analytics. Abstract. This study focuses on developing and applying methods/techniques in different aspects of the system for clinical text understanding, at both corpus and document level …

(Visited 266 times, 1 visits today)