Paraphrasing with Large Language Models

Witteveen, Sam; Andrews, Martin

doi:10.18653/v1/d19-5623

Cited by 55 publications

(41 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The model scored an F1-score of 76.2% with recall rate of 72.02% and precision 80.9%. For French tweets we used CamemBERT (Martin et al, 2019) from huggingface. The CamemBERT scored an F1-score of 76.32%, with recall rate of 71.45% and precision 81.91%.…”

Section: Discussionmentioning

confidence: 99%

Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing: Student Research Workshop

2021

View full text Add to dashboard Cite

Mentoring is at the heart of the SRW. In keeping with previous years, we had a pre-submission mentoring program before the submission deadline. A total of 36 papers participated in the pre-submission mentoring program. This program offered students the opportunity to receive comments from an experienced researcher to improve the writing style and presentation of their submissions.We are deeply grateful to the Swiss National Science Foundation (SNSF) for providing funds that covered student registrations. We thank our program committee members for their careful reviews of each paper

show abstract

Section: Discussionmentioning

confidence: 99%

Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing: Student Research Workshop

2021

View full text Add to dashboard Cite

show abstract

“…This brings us to other areas of research that are very related to our task: automatic paraphrasing (Wieting et al, 2015;Witteveen and Andrews, 2019), as well as research in diverse beam search methods (Vijayakumar et al, 2016;Li et al, 2016) for decoding multiple natural language outputs. We are happy that this shared task can serve as a forum for studying the intersection of these problems, and it is our hope that the STAPLE task data will continue to foster research in all of these areas.…”

Section: Related Workmentioning

confidence: 99%

Simultaneous Translation and Paraphrase for Language Education

Mayhew

Bicknell

Brust

et al. 2020

Proceedings of the Fourth Workshop on Neural Generation and Translation

View full text Add to dashboard Cite

We present the task of Simultaneous Translation and Paraphrasing for Language Education (STAPLE). Given a prompt in one language, the goal is to generate a diverse set of correct translations that language learners are likely to produce. This is motivated by the need to create and maintain large, high-quality sets of acceptable translations for exercises in a language-learning application, and synthesizes work spanning machine translation, MT evaluation, automatic paraphrasing, and language education technology.We developed a novel corpus with unique properties for five languages (Hungarian, Japanese, Korean, Portuguese, and Vietnamese), and report on the results of a shared task challenge which attracted 20 teams to solve the task. In our meta-analysis, we focus on three aspects of the resulting systems: external training corpus selection, model architecture and training decisions, and decoding and filtering strategies. We find that strong systems start with a large amount of generic training data, and then finetune with in-domain data, sampled according to our provided learner response frequencies.

show abstract

“…This brings us to other areas of research that are very related to our task: automatic paraphrasing (Wieting et al, 2015;Witteveen and Andrews, 2019), as well as research in diverse beam search methods for decoding multiple natural language outputs. We are happy that this shared task can serve as a forum for studying the intersection of these problems, and it is our hope that the STAPLE task data will continue to foster research in all of these areas.…”

Section: Related Workmentioning

confidence: 99%

Proceedings of the Fourth Workshop on Neural Generation and Translation

2020

View full text Add to dashboard Cite

We describe the finding of the Fourth Workshop on Neural Generation and Translation, held in concert with the annual conference of the Association for Computational Linguistics (ACL 2020). First, we summarize the research trends of papers presented in the proceedings. Second, we describe the results of the three shared tasks 1) efficient neural machine translation (NMT) where participants were tasked with creating NMT systems that are both accurate and efficient, and 2) document-level generation and translation (DGT) where participants were tasked with developing systems that generate summaries from structured data, potentially with assistance from text in another language and 3) STAPLE task: creation of as many possible translations of a given input text. This last shared task was organised by Duolingo.1 BLEU+case.mixed+lang.en-de+numrefs.1+s mooth.exp+test.wmt * +tok.13a+version.1.4.8 for various WMT test sets 2 Participants are likely to have used these test sets in development. The WMT 2020 test set was not yet available and others were out of the domain the systems were trained for.

show abstract

Paraphrasing with Large Language Models

Cited by 55 publications

References 16 publications

Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing: Student Research Workshop

Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing: Student Research Workshop

Simultaneous Translation and Paraphrase for Language Education

Proceedings of the Fourth Workshop on Neural Generation and Translation

Contact Info

Product

Resources

About