Zobrazeno 1 - 6
of 6
pro vyhledávání: '"Rishi Bommasani"'
Publikováno v:
Annals of the New York Academy of Sciences.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6ae3d422a7c59c215818a17bc1441c10
https://doi.org/10.1111/nyas.15007
https://doi.org/10.1111/nyas.15007
Publikováno v:
Extended Abstracts of the 2023 CHI Conference on Human Factors in Computing Systems.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b99eda6eee594c0995a83d28b85325f8
https://doi.org/10.1145/3544549.3583177
https://doi.org/10.1145/3544549.3583177
Publikováno v:
ACL
Contextualized representations (e.g. ELMo, BERT) have become the default pretrained representations for downstream NLP applications. In some settings, this transition has rendered their static embedding predecessors (e.g. Word2Vec, GloVe) obsolete. A
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a93ec3bfe1f7c06df8e9d804189603ae
https://doi.org/10.18653/v1/2020.acl-main.431
https://doi.org/10.18653/v1/2020.acl-main.431
Autor:
Rishi Bommasani, Claire Cardie
Publikováno v:
EMNLP (1)
High quality data forms the bedrock for building meaningful statistical models in NLP. Consequently, data quality must be evaluated either during dataset construction or *post hoc*. Almost all popular summarization datasets are drawn from natural sou
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1ddc456b75913ee3c867b65d033a45c5
https://doi.org/10.18653/v1/2020.emnlp-main.649
https://doi.org/10.18653/v1/2020.emnlp-main.649
Autor:
Rishi Bommasani
Publikováno v:
ACL (2)
Neural models at the sentence level often operate on the constituent words/tokens in a way that encodes the inductive bias of processing the input in a similar fashion to how humans do. However, there is no guarantee that the standard ordering of wor
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f715e04c3164e35a96bc699598eb3c23
https://doi.org/10.18653/v1/p19-2012
https://doi.org/10.18653/v1/p19-2012
Publikováno v:
SPNLP@NAACL-HLT
We propose structured encoding as a novel approach to learning representations for relations and events in neural structured prediction. Our approach explicitly leverages the structure of available relation and event metadata to generate these repres
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a93cca9b8c36d936dfa9aef1c967769f
https://doi.org/10.18653/v1/w19-1503
https://doi.org/10.18653/v1/w19-1503