Zobrazeno 1 - 10
of 271
pro vyhledávání: '"Christopher A. Manning"'
Publikováno v:
Computational Linguistics, Vol 47, Iss 2, Pp 255-308 (2021)
AbstractUniversal dependencies (UD) is a framework for morphosyntactic annotation of human language, which to date has been used to create treebanks for more than 100 languages. In this article, we outline the linguistic theory of the UD framework, w
Externí odkaz:
https://doaj.org/article/6400766c45a547859f20d741f3a82ea9
Publikováno v:
Proc Natl Acad Sci U S A
This paper explores the knowledge of linguistic structure learned by large artificial neural networks, trained via self-supervision, whereby the model simply tries to predict a masked word in a given context. Human language communication is via seque
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8142efd38705fb62fdc0ad6cad70a4ef
https://doi.org/10.1073/pnas.1907367117
https://doi.org/10.1073/pnas.1907367117
Automated fact-checking is a needed technology to curtail the spread of online misinformation. One current framework for such solutions proposes to verify claims by retrieving supporting or refuting evidence from related textual sources. However, the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1709e76d8190b80adcff78fb8b541420
http://arxiv.org/abs/2202.09381
http://arxiv.org/abs/2202.09381
Publikováno v:
Transactions of the Association for Computational Linguistics, Vol 7, Pp 249-266 (2019)
Humans gather information by engaging in conversations involving a series of interconnected questions and answers. For machines to assist in information gathering, it is therefore essential to enable them to answer conversational questions. We introd
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f8836bf023cbc1ac99e1486b7a4c4d41
https://www.mitpressjournals.org/doi/abs/10.1162/tacl_a_00266
https://www.mitpressjournals.org/doi/abs/10.1162/tacl_a_00266
Autor:
Liz Drysdale, Robyn Maxwell, Ari J. Adipurwawidjana, Christopher D. Manning, Sudarno Sumarto, Anne Booth, Hal Hill, John T. Maxwell, Helen Lok
Publikováno v:
Bulletin of Indonesian Economic Studies. 55:249-258
Joan Hardjono was a remarkable Australian-born Indonesian: a Sydney University honours graduate at 19; off to Indonesia as a Volunteer Graduate at 20; devoted wife, mother, and grandmother; rigorou...
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::35522e68fbf2fbb51bb7a6a98460c96c
https://doi.org/10.1080/00074918.2019.1640715
https://doi.org/10.1080/00074918.2019.1640715
Publikováno v:
NAACL-HLT
This work aims to build a dialogue agent that can weave new factual content into conversations as naturally as humans. We draw insights from linguistic principles of conversational analysis and annotate human-human conversations from the Switchboard
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e6cb71a2f989788b293d22cc7054ad0e
http://arxiv.org/abs/2104.07831
http://arxiv.org/abs/2104.07831
Publikováno v:
Proceedings of the 1st Workshop on NLP for Positive Impact.
Information extraction and question answering have the potential to introduce a new paradigm for how machine learning is applied to criminal law. Existing approaches generally use tabular data for predictive metrics. An alternative approach is needed
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6c6bbc483eb69d870c2118c14677f7fe
https://doi.org/10.18653/v1/2021.nlp4posimpact-1.8
https://doi.org/10.18653/v1/2021.nlp4posimpact-1.8
Publikováno v:
NAACL-HLT
Meta-learning promises few-shot learners that can adapt to new distributions by repurposing knowledge acquired from previous training. However, we believe meta-learning has not yet succeeded in NLP due to the lack of a well-defined task distribution,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6df5f31f25ac62ee480ed37cd65f3ec0
https://doi.org/10.18653/v1/2021.naacl-main.88
https://doi.org/10.18653/v1/2021.naacl-main.88
Publikováno v:
ACL/IJCNLP (1)
Active learning promises to alleviate the massive data needs of supervised machine learning: it has successfully improved sample efficiency by an order of magnitude on traditional tasks like topic classification and object recognition. However, we un
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::66ac677c25de330dcc85c513270d5397
https://doi.org/10.18653/v1/2021.acl-long.564
https://doi.org/10.18653/v1/2021.acl-long.564
Publikováno v:
EMNLP (1)
We introduce Sentence-level Language Modeling, a new pre-training objective for learning a discourse language representation in a fully self-supervised manner. Recent pre-training methods in NLP focus on learning either bottom or top-level language r
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d2eee506f0cb205c65d9d26969ab0fcd
https://doi.org/10.18653/v1/2020.emnlp-main.120
https://doi.org/10.18653/v1/2020.emnlp-main.120