Filters








9 Hits in 10.8 sec

DoCoGen: Domain Counterfactual Generation for Low Resource Domain Adaptation [article]

Nitay Calderon and Eyal Ben-David and Amir Feder and Roi Reichart
2022 arXiv   pre-print
Our model outperforms strong baselines and improves the accuracy of a state-of-the-art unsupervised DA algorithm.  ...  Natural language processing (NLP) algorithms have become very successful, but they still struggle when applied to out-of-distribution examples.  ...  Acknowledgements We would like to thank the action editor and the reviewers, as well as the members of the IE@Technion NLP group for their valuable feedback and advice.  ... 
arXiv:2202.12350v2 fatcat:7uomvkwjuvcctpghiy5kxbcnpe

Augmented Natural Language for Generative Sequence Labeling [article]

Ben Athiwaratkun, Cicero Nogueira dos Santos, Jason Krone, Bing Xiang
2020 arXiv   pre-print
We set a new state-of-the-art for few-shot slot labeling, improving substantially upon the previous 5-shot (75.0%→ 90.9%) and 1-shot (70.4%→ 81.0%) state-of-the-art results.  ...  We also maintain competitive results on high-resource tasks, performing within two points of the state-of-the-art on all tasks and setting a new state-of-the-art on the SNIPS dataset.  ...  In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2019, Minneapolis, MN, USA, June 2-7, 2019  ... 
arXiv:2009.13272v1 fatcat:4l2wynwy3zbjpnb2qh6fim6mie

Unsupervised Text Summarization via Mixed Model Back-Translation [article]

Yacine Jernite
2019 arXiv   pre-print
Our system outperforms the current state-of-the-art for unsupervised sentence summarization from fully unaligned data by over 2 ROUGE, and matches the performance of recent semi-supervised approaches.  ...  We present several initial models which rely on the asymmetrical nature of the task to perform the first back-translation step, and demonstrate the value of combining the data created by these diverse  ...  In Hu- man Language Technology Conference of the North American Chapter of the Association for Compu- tational Linguistics, HLT-NAACL 2003, Edmonton, Canada, May 27 -June 1, 2003.  ... 
arXiv:1908.08566v1 fatcat:nx5i2l3bhbhnjb4n3hzp2gzkai

A Survey of Deep Active Learning [article]

Pengzhen Ren, Yun Xiao, Xiaojun Chang, Po-Yao Huang, Zhihui Li, Brij B. Gupta, Xiaojiang Chen, Xin Wang
2021 arXiv   pre-print
In recent years, due to the rapid development of internet technology, we are in an era of information torrents and we have massive amounts of data.  ...  Deep learning (DL) is greedy for data and requires a large amount of data supply to optimize massive parameters, so that the model learns how to extract high-quality features.  ...  In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2019, Minneapolis, MN, USA, June  ... 
arXiv:2009.00236v2 fatcat:zuk2doushzhlfaufcyhoktxj7e

Discourse in Statistical Machine Translation

Christian Hardmeier
2012 Discours  
We demonstrate the viability of this decoding approach for different document-level models. From a linguistic viewpoint, we focus on the problem of translating pronominal anaphora.  ...  By creating a framework for experimenting with discourse-level features in SMT, this work contributes to a long-term perspective that strives for more thorough modelling of complex linguistic phenomena  ...  In: Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology, Edmonton (Canada), 48-54.K ).  ... 
doi:10.4000/discours.8726 fatcat:gxkpd2ubvzbjna7f7hw62oicg4

DoCoGen: Domain Counterfactual Generation for Low Resource Domain Adaptation

Nitay Calderon, Eyal Ben-David, Amir Feder, Roi Reichart
2022 Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)   unpublished
Our model outperforms strong baselines and improves the accuracy of a state-of-the-art unsupervised DA algorithm. 1  ...  Natural language processing (NLP) algorithms have become very successful, but they still struggle when applied to out-of-distribution examples.  ...  Acknowledgements We would like to thank the action editor and the reviewers, as well as the members of the IE@Technion NLP group for their valuable feedback and advice.  ... 
doi:10.18653/v1/2022.acl-long.533 fatcat:lkukck3wn5d4hdcbn6xidk7smm

Assessing Two-Mode Semantic Network Story Representations Using a False Memory Paradigm *

Steven Corman, B Hunter Ball, Kimberly Talboom, Gene Brewer
unpublished
This paper describes a novel method of representing semantic networks of stories (and other text) as a two-mode graph.  ...  Implications for further research and two-mode semantic representations are discussed. 1998 ACM Subject Classification I.2.4 Knowledge Representation Formalisms and Methods  ...  In HLT-NAACL 2003, Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics, May 27-June 1, Edmonton, Canada, Companion Volume: Demonstrations  ... 
fatcat:x7wizm7xpzekxizsyehaw4l44y

Workshop Crossing Barriers in Text Summarization Research

Horacio Saggion, Jean-Luc Borovets, Bulgaria, Horacio Saggion, Choy-Kim Chuah, Gustavo Crispino, Donna Harman, Min-Yen Kan, Guy Lapalme, Constantin Orasan, Dragomir Radev, Stan Szpakowicz (+5 others)
2005 unpublished
The availability of massive on-line textual and multimedia databases and the development of the Internet have made of Text Summarization not only an indispensable technology but also an active and interesting  ...  Since the 1993 Dagstuhl Seminar on Text Summarization for Intelligent Communication, the international research community has made outstanding contributions to Text Summarization, however as a result of  ...  Acknowledgements This work is funded by the Netherlands Organization for Scientific Research (NWO).  ... 
fatcat:7zll7mvjoff6bojgqvcercnxpy

OASIcs, Volume 51, SLATE'16, Complete Volume [article]

Marjan Mernik, José Paulo Leal, Hugo Gonçalo Oliveira
2016
The authors would like to thank the reviewers for their comments, insights and corrections.  ...  In Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics, NAACL'09, pages 19-27, Stroudsburg, PA, USA, 2009  ...  Edmonton, Canada, 2003.  ... 
doi:10.4230/oasics.slate.2016 fatcat:qwq6caaekncqfa52q4dntmci64