Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Yftah Ziser"'
Publikováno v:
Transactions of the Association for Computational Linguistics, Vol 11, Pp 488-510 (2023)
AbstractWe present the Assignment-Maximization Spectral Attribute removaL (AMSAL) algorithm, which erases information from neural representations when the information to be erased is implicit rather than directly being aligned to each input example.
Externí odkaz:
https://doaj.org/article/3c27e2521a484a1f85f100bee317dc8c
Publikováno v:
ACL/IJCNLP (2)
Recent works made significant advances on summarization tasks, facilitated by summarization datasets. Several existing datasets have the form of coherent-paragraph summaries. However, these datasets were curated from academic documents that were writ
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c88d68225774c3654098b6d73a1ded1c
https://doi.org/10.18653/v1/2021.acl-short.28
https://doi.org/10.18653/v1/2021.acl-short.28
Publikováno v:
NAACL-HLT
Predicting the answer to a product-related question is an emerging field of research that recently attracted a lot of attention. Answering subjective and opinion-based questions is most challenging due to the dependency on customer-generated content.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bde762519d9e27e4ce2d378c7ac5d8f8
Publikováno v:
SIGIR
Community question-answering (CQA) has been established as a prominent web service enabling users to post questions and get answers from the community. Product Question Answering (PQA) is a special CQA framework where questions are asked (and are ans
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ca8fbd4e835ba0cb4f7a9074e37754a8
https://doi.org/10.1145/3397271.3401077
https://doi.org/10.1145/3397271.3401077
Autor:
Yftah Ziser, Roi Reichart
Publikováno v:
ACL (1)
Pivot Based Language Modeling (PBLM) (Ziser and Reichart, 2018a), combining LSTMs with pivot-based methods, has yielded significant progress in unsupervised domain adaptation. However, this approach is still challenged by the large pivot detection pr
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9a613371e1746aeaf8f54d3f17c10a44
https://doi.org/10.18653/v1/p19-1591
https://doi.org/10.18653/v1/p19-1591
Autor:
Yftah Ziser, Roi Reichart
Publikováno v:
NAACL-HLT
Representation learning with pivot-based methods and with Neural Networks (NNs) have lead to significant progress in domain adaptation for Natural Language Processing. However, most previous work that follows these approaches does not explicitly expl
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::95427b9fd1b6616723708f867930bfd6
https://doi.org/10.18653/v1/n18-1112
https://doi.org/10.18653/v1/n18-1112
Autor:
Roi Reichart, Yftah Ziser
Publikováno v:
EMNLP
While cross-domain and cross-language transfer have long been prominent topics in NLP research, their combination has hardly been explored. In this work we consider this problem, and propose a framework that builds on pivot-based learning, structure-
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::53fbc00862b750767331054c092d11ff
https://doi.org/10.18653/v1/d18-1022
https://doi.org/10.18653/v1/d18-1022