285 Hits in 6.5 sec

How Would You Say It? Eliciting Lexically Diverse Dialogue for Supervised Semantic Parsing

Abhilasha Ravichander, Thomas Manzini, Matthias Grabmair, Graham Neubig, Jonathan Francis, Eric Nyberg
2017 Proceedings of the 18th Annual SIGdial Meeting on Discourse and Dialogue  
In this work, we present a methodology that elicits meaningful and lexically diverse queries from users for semantic parsing tasks.  ...  Building dialogue interfaces for realworld scenarios often entails training semantic parsers starting from zero examples.  ...  We would also like to thank Alan Black and Carolyn Rose for helpful discussions and Shruti Rijhwani, Rajat Kulshreshtha and Pengcheng Yin for their suggestions on the writing of this paper.  ... 
doi:10.18653/v1/w17-5545 dblp:conf/sigdial/RavichanderMGNF17 fatcat:sazf2nq3mvf6lp47wchmud4qhq

Message from the general chair

Benjamin C. Lee
2015 2015 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS)  
We propose a candidate ranking model for "this-issue" anaphora resolution that explores different "issue"-specific and general abstract-anaphora features. The model is not restricted to nominal  ...  Joint Learning for Coreference Resolution with Markov Logic Resolving "This-issue" Anaphora Varada Kolhatkar and Graeme Hirst Saturday 12:00pm-12:30pm -202 A (ICC) We annotate and resolve a particular  ...  A key insight in our approach is to reduce the tasks of content selection ("what to say") and surface realization ("how to say") into a common parsing problem.  ... 
doi:10.1109/ispass.2015.7095776 dblp:conf/ispass/Lee15 fatcat:ehbed6nl6barfgs6pzwcvwxria

Robots That Use Language

Stefanie Tellex, Nakul Gopalan, Hadas Kress-Gazit, Cynthia Matuszek
2020 Annual Review of Control Robotics and Autonomous Systems  
Finally, we describe several application domains for language-using robots.  ...  Please see for revised estimates.  ...  For example, one route direction corpus contains the instruction "you will see a nice view," referring to a view out of a set of windows the robot would pass.  ... 
doi:10.1146/annurev-control-101119-071628 fatcat:gljaeee7pvhb3ohuur3agdvvyq

Key-Value Retrieval Networks for Task-Oriented Dialogue

Mihail Eric, Lakshmi Krishnan, Francois Charette, Christopher D. Manning
2017 Proceedings of the 18th Annual SIGdial Meeting on Discourse and Dialogue  
Neural task-oriented dialogue systems often struggle to smoothly interface with a knowledge base.  ...  The model is end-to-end differentiable and does not need to explicitly model dialogue state or belief trackers.  ...  Acknowledgments The authors wish to thank He He, Peng Qi, Urvashi Khandelwal, and Reid Pryzant for their valuable feedback and insights.  ... 
doi:10.18653/v1/w17-5506 dblp:conf/sigdial/EricKCM17 fatcat:fglbnktosjdrvpd2xdlgn6gh4m

KLUE: Korean Language Understanding Evaluation [article]

Sungjoon Park, Jihyung Moon, Sungdong Kim, Won Ik Cho, Jiyoon Han, Jangwon Park, Chisung Song, Junseong Kim, Yongsook Song, Taehwan Oh, Joohong Lee, Juhyun Oh (+19 others)
2021 arXiv   pre-print
We build all of the tasks from scratch from diverse source corpora while respecting copyrights, to ensure accessibility for anyone without any restrictions.  ...  , Machine Reading Comprehension, and Dialogue State Tracking.  ...  In addition, we appreciate The Korea Economy Daily and Acrofan for supporting their news articles for MRC datasets.  ... 
arXiv:2105.09680v4 fatcat:ejkvhzfldzhcbkhw4eakm7s634

Survey of the State of the Art in Natural Language Generation: Core tasks, applications and evaluation [article]

Albert Gatt, Emiel Krahmer
2018 arXiv   pre-print
Acknowledgements We thank the four reviewers for their detailed and constructive comments.  ...  EK received support from RAAK-PRO SIA (2014-01-51PRO) and The Netherlands Organization for Scientific Research (NWO 360-89-050), which is gratefully acknowledged.  ...  You would probably enjoy these restaurants.  ... 
arXiv:1703.09902v4 fatcat:owx2fgo2bjej3b27ve2f3ledoe

Survey of the State of the Art in Natural Language Generation: Core tasks, applications and evaluation

Albert Gatt, Emiel Krahmer
2018 The Journal of Artificial Intelligence Research  
Acknowledgments We thank the four reviewers for their detailed and constructive comments.  ...  EK received support from RAAK-PRO SIA (2014-01-51PRO) and The Netherlands Organization for Scientific Research (NWO 360-89-050), which is gratefully acknowledged.  ...  You would probably enjoy these restaurants.  ... 
doi:10.1613/jair.5477 fatcat:ycuteghjzncn7nx6pzkhzd6mn4

Natural Language Parsing as Statistical Pattern Recognition [article]

David M. Magerman
1994 arXiv   pre-print
In this work, I propose an automatic method for acquiring a statistical parser from a set of parsed sentences which takes advantage of some initial linguistic input, but avoids the pitfalls of the iterative  ...  These decision trees take advantage of significant amount of contextual information, potentially including all of the lexical information in the sentence, to produce highly accurate statistical models  ...  Now, if you were a tree, which kind would you be?  ... 
arXiv:cmp-lg/9405009v2 fatcat:2qh6ft7wyndmvfjgzhaiz6qefu

Automatic Sarcasm Detection: A Survey [article]

Aditya Joshi, Pushpak Bhattacharyya, Mark James Carman
2016 arXiv   pre-print
We observe three milestones in the research so far: semi-supervised pattern extraction to identify implicit sentiment, use of hashtag-based supervision, and use of context beyond target text.  ...  In terms of resources that could be useful for understanding state-of-the-art, the survey presents several useful illustrations - most prominently, a table that summarizes past papers along different dimensions  ...  p: You have done a good job at the assignment. p': You have done a bad job at the assignment. (4) Eisterhold et al. [2006] state that sarcasm can be understood in terms of the response it elicits.  ... 
arXiv:1602.03426v2 fatcat:ypdu2fvtlvcrva77r7yechq5bu

An integrated theory of language production and comprehension

Martin J. Pickering, Simon Garrod
2013 Behavioral and Brain Sciences  
Importantly, they incorporate well-defined levels of linguistic representation (such as semantics, syntax, and phonology).  ...  We then consider the evidence for interweaving in action, action perception, and joint action, and explain such evidence in terms of prediction.  ...  We thank Marieke Longcamp for comments and Dashiel Munding for comments and native proofreading How do forward models work? And why would you want them?  ... 
doi:10.1017/s0140525x12001495 pmid:23789620 fatcat:iysayp5tujgffkbwtjwxx23e3m

Multi-Dimensional Gender Bias Classification [article]

Emily Dinan, Angela Fan, Ledell Wu, Jason Weston, Douwe Kiela, Adina Williams
2020 arXiv   pre-print
Distinguishing between gender bias along multiple dimensions is important, as it enables us to train finer-grained gender bias classifiers.  ...  We show our classifiers prove valuable for a variety of important applications, such as controlling for gender bias in generative models, detecting gender bias in arbitrary text, and shed light on offensive  ...  Original: just checking up on you by saying hi Rewrite: Hanna said she was just checking up on you by saying hi Original: How are you doing today Jahsim? Rewrite: How are you doing today Mr. Jahsim?  ... 
arXiv:2005.00614v1 fatcat:o3lgzjeouvhepmp6bkmw2jk7jm

Spoken Language Interaction with Virtual Agents and Robots (SLIVAR): Towards Effective and Ethical Interaction (Dagstuhl Seminar 20021)

Laurence Devillers, Tatsuya Kawahara, Roger K. Moore, Matthias Scheutz
2020 Dagstuhl Reports  
In this report, we present an overview of the seminar program and its outcomes, abstracts from stimulus talks given by prominent researchers, a summary of the 'Show and Tell' demonstrations held during  ...  If you are alone and unhappy, the robot could joke to comfort you; if you are angry, it could help you to put things into perspective, saying that the situation is not so bad.  ...  Today our job is to create the illusion that you are talking with something that understands you and cares about what you are saying. Which it doesn't.  ... 
doi:10.4230/dagrep.10.1.1 dblp:journals/dagstuhl-reports/DevillersKMS20 fatcat:yjjvsdl3xzec5mldakylcfinbi

Program Committee

2006 2006 Sixth IEEE International Workshop on Source Code Analysis and Manipulation  
The invited papers were One Million Sense-Tagged Instances for Word Sense Disambiguation and Induction by Ng Hwee Tou (National University of Singapore), How are you two related?  ...  Corpus-based Learning of Lexical Semantic Relations by Vered Shwartz (Bar-Ilan University), Inducing Interpretable Word Senses for WSD and Enrichment of Lexical Resources by Alexander Panchenko (University  ...  Acknowledgements The authors would like to thank and acknowledge the support and help by the members of Center for Indian Language Technology (CFILT) 11 and Hindi Shabdamitra team.  ... 
doi:10.1109/scam.2006.23 dblp:conf/scam/X06c fatcat:2dhsf7loj5hlffu2jxpmlo2qcq

Artificial Intelligence, speech and language processing approaches to monitoring Alzheimer's Disease: a systematic review [article]

Sofia de la Fuente Garcia, Craig Ritchie, Saturnino Luz
2020 arXiv   pre-print
Consequently, speech and language data have been extensively studied in connection with its diagnosis.  ...  Language is a valuable source of clinical information in Alzheimer's Disease, as it declines concurrently with neurodegeneration.  ...  Acknowledgements We thank Marshall Dozier, the Academic Support Librarian for her help with the search queries and the PROSPERO protocol.  ... 
arXiv:2010.06047v1 fatcat:gowcdpj6pfddfns3gh7amtqpze

Dynamic Search – Optimizing the Game of Information Seeking [article]

Zhiwen Tang, Grace Hui Yang
2021 arXiv   pre-print
Details are given for how different approaches are used to model interactions among the human user, the search system, and the environment.  ...  To position dynamic search in a larger research landscape, the article discusses in detail its relationship to related research topics and disciplines.  ...  ACKNOWLEDGMENTS The authors would like to thank Ian Soboroff, Jiyun Luo, Shiqi Liu, Angela Yang, and Xuchu Dong for their past efforts during our long-term collaboration on dynamic search.  ... 
arXiv:1909.12425v2 fatcat:mdby4xq4jrg4pm6jpxslsv2sri
« Previous Showing results 1 — 15 out of 285 results