Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Jennimaria Palomaki"'
Autor:
Eunsol Choi, Jennimaria Palomaki, Matthew Lamm, Tom Kwiatkowski, Dipanjan Das, Michael Collins
Publikováno v:
Transactions of the Association for Computational Linguistics, Vol 9, Pp 447-461 (2021)
AbstractModels for question answering, dialogue agents, and summarization often interpret the meaning of a sentence in a rich context and use that meaning in a new context. Taking excerpts of text can be problematic, as key pieces may not be explicit
Externí odkaz:
https://doaj.org/article/11adf072854d4f76b1297e759d7db650
Autor:
Matthew Lamm, Jennimaria Palomaki, Chris Alberti, Daniel Andor, Eunsol Choi, Livio Baldini Soares, Michael Collins
Publikováno v:
Transactions of the Association for Computational Linguistics, Vol 9, Pp 790-806 (2021)
A question answering system that in addition to providing an answer provides an explanation of the reasoning that leads to that answer has potential advantages in terms of debuggability, extensibility, and trust. To this end, we propose QED, a lingui
Externí odkaz:
https://doaj.org/article/06787832af234ed685bae92217b8247a
Autor:
Matthew Lamm, Dipanjan Das, Tom Kwiatkowski, Eunsol Choi, Michael Collins, Jennimaria Palomaki
Publikováno v:
Transactions of the Association for Computational Linguistics. 9:447-461
Models for question answering, dialogue agents, and summarization often interpret the meaning of a sentence in a rich context and use that meaning in a new context. Taking excerpts of text can be problematic, as key pieces may not be explicit in a lo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0ac620e531058e4a658be9e2034b1b9c
https://doi.org/10.1162/tacl_a_00377
https://doi.org/10.1162/tacl_a_00377
Autor:
Jennimaria Palomaki, Jonathan H. Clark, Tom Kwiatkowski, Eunsol Choi, Michael Collins, Vitaly Nikolaev, Dan Garrette
Publikováno v:
Transactions of the Association for Computational Linguistics. 8:454-470
Confidently making progress on multilingual modeling requires challenging, trustworthy evaluations. We present TyDi QA—a question answering dataset covering 11 typologically diverse languages with 204K question-answer pairs. The languages of TyDi Q
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d0fa0a2d60d65e9c4928bb4b544808a6
https://doi.org/10.1162/tacl_a_00317
https://doi.org/10.1162/tacl_a_00317
Autor:
Chris Alberti, Jennimaria Palomaki, Quoc V. Le, Jakob Uszkoreit, Danielle Epstein, Ankur P. Parikh, Slav Petrov, Kristina Toutanova, Olivia Redfield, Illia Polosukhin, Kenton Lee, Llion Jones, Michael Collins, Ming-Wei Chang, Andrew M. Dai, Matthew Kelcey, Jacob Devlin, Tom Kwiatkowski
Publikováno v:
Transactions of the Association for Computational Linguistics, Vol 7, Pp 453-466 (2019)
We present the Natural Questions corpus, a question answering data set. Questions consist of real anonymized, aggregated queries issued to the Google search engine. An annotator is presented with a question along with a Wikipedia page from the top 5
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::63a711a2e1b76471aebe0fe51dea5eea
https://doi.org/10.1162/tacl_a_00276
https://doi.org/10.1162/tacl_a_00276
Publikováno v:
EMNLP (1)
Natural language inference (NLI) data has proven useful in benchmarking and, especially, as pretraining data for tasks requiring language understanding. However, the crowdsourcing protocol that was used to collect this data has known issues and was n
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0f567b417aefd3406c27cf389651810b
http://arxiv.org/abs/2004.11997
http://arxiv.org/abs/2004.11997
Autor:
Eunsol Choi, Matthew Lamm, Jennimaria Palomaki, Daniel Andor, Livio Soares, Michael Collins, Chris Alberti
A question answering system that in addition to providing an answer provides an explanation of the reasoning that leads to that answer has potential advantages in terms of debuggability, extensibility and trust. To this end, we propose QED, a linguis
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4a1ac85e9120cc867f49d2f92a2925dc