Filters








87 Hits in 9.9 sec

Deep Learning for Text Style Transfer: A Survey

Di Jin, Zhijing Jin, Zhiting Hu, Olga Vechtomova, Rada Mihalcea
2021 Computational Linguistics  
It has a long history in the field of natural language processing, and recently has re-gained significant attention thanks to the promising performance brought by deep neural models.  ...  We also provide discussions on a variety of important topics regarding the future development of this task.  ...  The NAACL-HLT 2021, Online, June 6-11, 2021, bilingualism reader, 18(2):221–256.  ... 
doi:10.1162/coli_a_00426 fatcat:v7vmb62ckfcu5k5mpu2pydnrxy

What to Pre-Train on? Efficient Intermediate Task Selection [article]

Clifton Poth, Jonas Pfeiffer, Andreas Rücklé, Iryna Gurevych
2021 arXiv   pre-print
With an abundance of candidate datasets as well as pre-trained language models, it has become infeasible to run the cross-product of all combinations to find the best transfer setting.  ...  Our best methods achieve an average Regret@3 of less than 1% across all target tasks, demonstrating that we are able to efficiently identify the best datasets for intermediate training.  ...  We thank Leonardo Ribeiro and the anonymous reviewers for insightful feedback and suggestions on a draft of this paper.  ... 
arXiv:2104.08247v2 fatcat:4ljcfshev5f3tmgugrrrkh3s4m

A Tutorial on Evaluation Metrics used in Natural Language Generation

Mitesh M. Khapra, Ananya B. Sai
2021 Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Tutorials   unpublished
There has been a massive surge of Natural Language Generation (NLG) models in the recent years, accelerated by deep learning and the availability of large-scale datasets.  ...  Especially in the last few years, there has been an increasing focus on evaluation metrics, with several criticisms of existing metrics and proposals for several new metrics.  ...  In 11th Conference of the European Chapter of the Association for Com- putational Linguistics, Trento, Italy. Association for Computational Linguistics.  ... 
doi:10.18653/v1/2021.naacl-tutorials.4 fatcat:nju2lewr35fyvlf72uwqqigpd4

Revisiting the Boundary between ASR and NLU in the Age of Conversational Dialog Systems

Manaal Faruqui, Dilek Hakkani-Tür
2021 Computational Linguistics  
In light of the observations we make in this paper, we argue that (1) NLU should be cognizant of the presence of ASR models being used upstream in a dialog system's pipeline, (2) ASR should be able to  ...  As more users across the world are interacting with dialog agents in their daily life, there is a need for better speech understanding that calls for renewed attention to the dynamics between research  ...  In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 3291–3301  ... 
doi:10.1162/coli_a_00430 fatcat:6yfhq4vv3fhhlmigf5hrwzt3ui

Understanding by Understanding Not: Modeling Negation in Language Models

Arian Hosseini, Siva Reddy, Dzmitry Bahdanau, R Devon Hjelm, Alessandro Sordoni, Aaron Courville
2021 Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies   unpublished
Negation is a core construction in natural language. Despite being very successful on many tasks, state-of-the-art pre-trained language models often handle negation incorrectly.  ...  To improve language models in this regard, we propose to augment the language modeling objective with an unlikelihood objective that is based on negated generic sentences from a raw text corpus.  ...  In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computa- tional Linguistics: Human Language Technologies, Volume 1 (Long Papers), pages 1195-1205, New Orleans  ... 
doi:10.18653/v1/2021.naacl-main.102 fatcat:m5lxzbkivrcjznqrxsgumspex4

Deep Learning for Text Style Transfer: A Survey [article]

Di Jin, Zhijing Jin, Zhiting Hu, Olga Vechtomova, Rada Mihalcea
2021 arXiv   pre-print
It has a long history in the field of natural language processing, and recently has re-gained significant attention thanks to the promising performance brought by deep neural models.  ...  We discuss the task formulation, existing datasets and subtasks, evaluation, as well as the rich methodologies in the presence of parallel and non-parallel data.  ...  The NAACL-HLT 2021, Online, June 6-11, 2021, bilingualism reader, 18(2):221–256.  ... 
arXiv:2011.00416v5 fatcat:wfw3jfh2mjfupbzrmnztsqy4ny

Contrastive Learning of Sociopragmatic Meaning in Social Media [article]

Chiyu Zhang, Muhammad Abdul-Mageed, Ganesh Jawahar
2022 arXiv   pre-print
Our framework outperforms other contrastive learning frameworks for both in-domain and out-of-domain data, across both the general and few-shot settings.  ...  Recent progress in representation and contrastive learning in NLP has not widely considered the class of sociopragmatic meaning (i.e., meaning in interaction within different language communities).  ...  Canada (SSHRC; 435-2018-0576; 895-2020-1004; 895-2021-1008), Canadian Foundation for Innovation (CFI; 37771), Compute Canada (CC), 12 and UBC ARC-Sockeye. 13 Any opinions, conclusions or recommendations  ... 
arXiv:2203.07648v2 fatcat:6zmhiogvirdlznoaqonyuesc54

Data Augmentation for Low-Resource Named Entity Recognition Using Backtranslation [article]

Usama Yaseen, Stefan Langer
2021 arXiv   pre-print
The state of art natural language processing systems relies on sizable training datasets to achieve high performance.  ...  In this work, we adapt backtranslation to generate high quality and linguistically diverse synthetic data for low-resource named entity recognition.  ...  In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2018, New Orleans, Louisiana, USA, June 1-6,  ... 
arXiv:2108.11703v1 fatcat:m2ovl4rgizbtxphzeneuhjcouq

A Survey on Recent Approaches for Natural Language Processing in Low-Resource Scenarios

Michael A. Hedderich, Lukas Lange, Heike Adel, Jannik Strötgen, Dietrich Klakow
2021 Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies   unpublished
As they are known for requiring large amounts of training data, there is a growing body of work to improve the performance in low-resource settings.  ...  Motivated by the recent fundamental changes towards neural models and the popular pre-train and fine-tune paradigm, we survey promising approaches for low-resource natural language processing.  ...  Acknowledgments The authors would like to thank Annemarie Friedrich for her valuable feedback and the anonymous reviewers for their helpful comments.  ... 
doi:10.18653/v1/2021.naacl-main.201 fatcat:xrgln55my5djxo3qqpzel3acuy

Extending Multi-Document Summarization Evaluation to the Interactive Setting

Ori Shapira, Ramakanth Pasunuru, Hadar Ronen, Mohit Bansal, Yael Amsterdamer, Ido Dagan
2021 Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies   unpublished
We demonstrate the use of our framework by evaluating and comparing baseline implementations that we developed for this purpose, which will serve as part of our benchmark.  ...  In this paper, we develop an end-to-end evaluation framework for interactive summarization, focusing on expansion-based interaction, which considers the accumulating information along a user session.  ...  In Proceedings of the Human Lan- guage Technology Conference of the North Ameri- can Chapter of the Association for Computational Linguistics: HLT-NAACL 2004, pages 145-152, Boston, Massachusetts, USA  ... 
doi:10.18653/v1/2021.naacl-main.54 fatcat:yiiwmt2ndfdq3kstob4i4nlo5e

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

Pushing on Text Readability Assessment: A Transformer Meets Handcrafted Linguistic Features [article]

Bruce W. Lee, Yoo Sung Jang, Jason Hyung-Jong Lee
2021 arXiv   pre-print
The use of handcrafted features help model performance on smaller datasets.  ...  Notably, our RoBERTA-RF-T1 hybrid achieves the near-perfect classification accuracy of 99%, a 20.3% increase from the previous SOTA.  ...  Partly funded by the 4th Industrial Revolution R&D Program, Min. of SMEs & Startups, Rep. of Korea.  ... 
arXiv:2109.12258v1 fatcat:6sdnrkkzrjanjnqmrgo5bqwgke

Few-shot and Zero-shot Approaches to Legal Text Classification: A Case Study in the Financial Sector

Rajdeep Sarkar, Atul Kr. Ojha, Jay Megaro, John Mariano, Vall Herard, John P. McCrae
2021 Zenodo  
The application of predictive coding techniques to legal texts has the potential to greatly reduce the cost of legal review of documents, however, there is such a wide array of legal tasks and continuously  ...  This method allows predictive coding methods to be rapidly developed for new regulations and markets.  ...  In Proceedings of the 58th An- June 6-11, 2021, pages 5493–5500. Association for nual Meeting of the Association for Computational Computational Linguistics.  ... 
doi:10.5281/zenodo.5772042 fatcat:sgkfcnqtmjainnvs3fyoqi4z2m

Combining Textual Features for the Detection of Hateful and Offensive Language [article]

Sherzod Hakimov, Ralph Ewerth
2021 arXiv   pre-print
In this paper, we present an analysis of combining different textual features for the detection of hateful or offensive posts on Twitter.  ...  The proposed architecture is evaluated on the English Subtask 1A: Identifying Hate, offensive and profane content from the post datasets of HASOC-2021 dataset under the team name TIB-VA.  ...  .), Proceedings of the 2019 Conference of the North American Chapter of the Association for Computa- tional Linguistics: Human Language Technologies, NAACL-HLT 2019, Minneapolis, MN, USA  ... 
arXiv:2112.04803v1 fatcat:nwvs4vongnhubk2thtk2xlwysu

TSDAE: Using Transformer-based Sequential Denoising Auto-Encoder for Unsupervised Sentence Embedding Learning [article]

Kexin Wang, Nils Reimers, Iryna Gurevych
2021 arXiv   pre-print
It can achieve up to 93.1% of the performance of in-domain supervised approaches.  ...  Further, we show that TSDAE is a strong domain adaptation and pre-training method for sentence embeddings, significantly outperforming other approaches like Masked Language Model.  ...  Acknowledgments This work has been supported by the German Research Foundation (DFG) as part of the UKP-SQuARE project (grant GU 798/29-1), by the Eu-  ... 
arXiv:2104.06979v3 fatcat:aw32qx352vbkdje43kpfwkcu6y
« Previous Showing results 1 — 15 out of 87 results