Zobrazeno 1 - 9
of 9
pro vyhledávání: '"Zeqiu Wu"'
Autor:
Zeqiu Wu, Ryu Parish, Hao Cheng, Sewon Min, Prithviraj Ammanabrolu, Mari Ostendorf, Hannaneh Hajishirzi
Publikováno v:
Transactions of the Association for Computational Linguistics, Vol 11, Pp 453-468 (2023)
AbstractIn an information-seeking conversation, a user may ask questions that are under-specified or unanswerable. An ideal agent would interact by initiating different response types according to the available knowledge sources. However, most curren
Externí odkaz:
https://doaj.org/article/ece55ee3d6294fe3b867f5436a755131
Autor:
Zeqiu Wu, Ryu Parish, Hao Cheng, Sewon Min, Prithviraj Ammanabrolu, Mari Ostendorf, Hannaneh Hajishirzi
Publikováno v:
Transactions of the Association for Computational Linguistics. 11:453-468
In an information-seeking conversation, a user may ask questions that are under-specified or unanswerable. An ideal agent would interact by initiating different response types according to the available knowledge sources. However, most current studie
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a0d1729a0a6f37c7f4b0a18608129e81
https://doi.org/10.1162/tacl_a_00559
https://doi.org/10.1162/tacl_a_00559
Identifying relevant knowledge to be used in conversational systems that are grounded in long documents is critical to effective response generation. We introduce a knowledge identification model that leverages the document structure to provide dialo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::fac1594fc1ee22f527618656fd44da9d
http://arxiv.org/abs/2109.04673
http://arxiv.org/abs/2109.04673
Publikováno v:
ACL/IJCNLP (Findings)
The advent of large pre-trained language models has made it possible to make high-quality predictions on how to add or change a sentence in a document. However, the high branching factor inherent to text generation impedes the ability of even the str
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4e7e5daba6b23ae0083ace15bf724722
http://arxiv.org/abs/2106.07192
http://arxiv.org/abs/2106.07192
Publikováno v:
WSDM
Automatic relation extraction (RE) for types of interest is of great importance for interpreting massive text corpora in an efficient manner. Traditional RE models have heavily relied on human-annotated corpus for training, which can be costly in gen
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a01dc81b399a51654b2aadb6bdae974d
https://doi.org/10.1145/3159652.3159709
https://doi.org/10.1145/3159652.3159709
Autor:
Zeqiu Wu
Publikováno v:
Mining Structures of Factual Knowledge from Text ISBN: 9783031007842
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5ae078b15314630a7248b13bd19cbc3e
https://doi.org/10.1007/978-3-031-01912-8_10
https://doi.org/10.1007/978-3-031-01912-8_10
Publikováno v:
Machine Learning and Knowledge Discovery in Databases ISBN: 9783319712482
ECML/PKDD (1)
ECML/PKDD (1)
Corpus-based set expansion (i.e., finding the “complete” set of entities belonging to the same semantic class, based on a given corpus and a tiny set of seeds) is a critical task in knowledge discovery. It may facilitate numerous downstream appli
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b881957f1f226f5892bdc6e5e82e6fe6
https://doi.org/10.1007/978-3-319-71249-9_18
https://doi.org/10.1007/978-3-319-71249-9_18
Autor:
Jiaming Shen, Jiawei Han, Fangbo Tao, Peipei Ping, David A. Liem, Xuan Wang, Richard M. Weinshilboum, Meng Jiang, Saurabh Sinha, Zeqiu Wu, Qi Zhu, Xiang Ren, Meng Qu
Publikováno v:
ACL (System Demonstrations)
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::33829e1dc2d75b52121f10ed8b37e2e2
https://doi.org/10.18653/v1/p17-4010
https://doi.org/10.18653/v1/p17-4010
Autor:
Zeqiu, Wu
Publikováno v:
Chinese Journal of Population Resources and Environment; January 2009, Vol. 7 Issue: 1 p82-88, 7p