Zobrazeno 1 - 10
of 11
pro vyhledávání: '"Rik Koncel-Kedziorski"'
Publikováno v:
ACL/IJCNLP (1)
We address the task of explaining relationships between two scientific documents using natural language text. This task requires modeling the complex content of long technical documents, deducing a relationship between these documents, and expressing
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::655362949261d4077079b3c609b46228
https://doi.org/10.18653/v1/2021.acl-long.166
https://doi.org/10.18653/v1/2021.acl-long.166
Personal attributes represent structured information about a person, such as their hobbies, pets, family, likes and dislikes. We introduce the tasks of extracting and inferring personal attributes from human-human dialogue, and analyze the linguistic
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::305913cc04cc7eb306cb0eac79bc1e7e
Autor:
Shanchuan Lin, Hannaneh Hajishirzi, Aida Amini, Rik Koncel-Kedziorski, Yejin Choi, Saadia Gabriel
Publikováno v:
NAACL-HLT (1)
We introduce a large-scale dataset of math word problems and an interpretable neural math problem solver by learning to map problems to their operation programs. Due to annotation challenges, current datasets in this domain have been either relativel
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e98c79e814d7c08baf7554f9a399613a
https://doi.org/10.18653/v1/n19-1245
https://doi.org/10.18653/v1/n19-1245
Publikováno v:
NAACL-HLT (1)
Generating texts which express complex ideas spanning multiple sentences requires a structured representation of their content (document plan), but these representations are prohibitively expensive to manually produce. In this work, we address the pr
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f8b1e75ee4e6a9c5c88b00ca6b59a548
https://doi.org/10.18653/v1/n19-1238
https://doi.org/10.18653/v1/n19-1238
Autor:
Rik Koncel-Kedziorski, Gabriel Stanovsky, Cristian Petrescu-Prahova, Ronan Le Bras, Hannaneh Hajishirzi, Mark Hopkins
Publikováno v:
SemEval@NAACL-HLT
We report on the SemEval 2019 task on math question answering. We provided a question set derived from Math SAT practice exams, including 2778 training questions and 1082 test questions. For a significant subset of these questions, we also provided S
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::16b28873b9916f2d7fc90df189bdaa70
https://doi.org/10.18653/v1/s19-2153
https://doi.org/10.18653/v1/s19-2153
Publikováno v:
Transactions of the Association for Computational Linguistics. 3:585-597
This paper formalizes the problem of solving multi-sentence algebraic word problems as that of generating and scoring equation trees. We use integer linear programming to generate equation trees and score their likelihood by learning local and global
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c18f4995bcfe188df989686bc8eb30e1
https://doi.org/10.1162/tacl_a_00160
https://doi.org/10.1162/tacl_a_00160
Publikováno v:
EMNLP
LSTMs are powerful tools for modeling contextual information, as evidenced by their success at the task of language modeling. However, modeling contexts in very high dimensional space can lead to poor generalizability. We introduce the Pyramidal Recu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b512adfa6ae9e445d1192a3794df5ba4
Publikováno v:
EMNLP
Texts present coherent stories that have a particular theme or overall setting, for example science fiction or western. In this paper, we present a text generation method called {\it rewriting} that edits existing human-authored narratives to change
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b74a3e601b33d3d25ff7b26393a6282e
https://doi.org/10.18653/v1/d16-1168
https://doi.org/10.18653/v1/d16-1168
Publikováno v:
EMNLP
Language is given meaning through its correspondence with a world representation. This correspondence can be at multiple levels of granularity or resolutions. In this paper, we introduce an approach to multi-resolution language grounding in the extre
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::bf7ba112a1a4a49cbb3058ac692f8dfe
https://doi.org/10.3115/v1/d14-1043
https://doi.org/10.3115/v1/d14-1043