QAmeleon: Multilingual QA with Only 5 Examples

Autor: Priyanka Agrawal, Chris Alberti, Fantine Huot, Joshua Maynez, Ji Ma, Sebastian Ruder, Kuzman Ganchev, Dipanjan Das, Mirella Lapata

Publikováno v: Transactions of the Association for Computational Linguistics, Vol 11 (2023)

Externí odkaz: https://doaj.org/article/8faa2d36a9fa414b8e03374b25025494

Planning with Learned Entity Prompts for Abstractive Summarization

Autor: Shashi Narayan, Yao Zhao, Joshua Maynez, Gonçalo Simões, Vitaly Nikolaev, Ryan McDonald

Publikováno v: Transactions of the Association for Computational Linguistics, Vol 9, Pp 1475-1492 (2021)

AbstractWe introduce a simple but flexible mechanism to learn an intermediate plan to ground the generation of abstractive summaries. Specifically, we prepend (or prompt) target summaries with entity chains—ordered sequences of entities mentioned i

Externí odkaz: https://doaj.org/article/6b04d20f306a41088885f7c5939a9f80

Data Augmentation for Low-Resource Dialogue Summarization

Autor: Yongtai Liu, Joshua Maynez, Gonçalo Simões, Shashi Narayan

Publikováno v: Findings of the Association for Computational Linguistics: NAACL 2022.

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::6cf173a7111d30de09d121f18955eb0c
https://doi.org/10.18653/v1/2022.findings-naacl.53

Focus Attention: Promoting Faithfulness and Diversity in Summarization

Autor: Ryan McDonald, Sascha Rothe, Rahul Aralikatte, Joshua Maynez, Shashi Narayan

Publikováno v: ACL/IJCNLP (1)
Aralikatte, R, Narayan, S, Maynez, J, Rothe, S & McDonald, R 2021, Focus attention : Promoting faithfulness and diversity in summarization . in ACL-IJCNLP 2021-59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, Proceedings of the Conference . Association for Computational Linguistics, pp. 6078-6095, Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, ACL-IJCNLP 2021, Virtual, Online, 01/08/2021 . https://doi.org/10.18653/v1/2021.acl-long.474

Professional summaries are written with document-level information, such as the theme of the document, in mind. This is in contrast with most seq2seq decoders which simultaneously learn to focus on salient content, while deciding what to generate, at

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9333312f70fafd66deb6825845736bf2
http://arxiv.org/abs/2105.11921

Stepwise Extractive Summarization and Planning with Structured Transformers

Autor: Daniele Pighin, Blaž Bratanič, Ryan McDonald, Shashi Narayan, Jakub Adamek, Joshua Maynez

Publikováno v: EMNLP (1)

We propose encoder-centric stepwise models for extractive summarization using structured transformers -- HiBERT and Extended Transformers. We enable stepwise summarization by injecting the previously generated summary into the structured transformer

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e6acbc6696ed13ab80901410c5129c98
http://arxiv.org/abs/2010.02744