Zobrazeno 1 - 10
of 16
pro vyhledávání: '"John Wieting"'
Semantic parsers map natural language utterances into meaning representations (e.g., programs). Such models are typically bottlenecked by the paucity of training data due to the required laborious annotation efforts. Recent studies have performed zer
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a481c796ecc638e848e95376c6104803
http://arxiv.org/abs/2110.08381
http://arxiv.org/abs/2110.08381
Publikováno v:
NAACL-HLT
In most cases, the lack of parallel corpora makes it impossible to directly train supervised models for the text style transfer task. In this paper, we explore training algorithms that instead optimize reward functions that explicitly consider differ
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5ffd5f59ecc23534077d913060a3c71b
http://arxiv.org/abs/2010.12771
http://arxiv.org/abs/2010.12771
Publikováno v:
Transactions of the Association for Computational Linguistics, Vol 8, Pp 109-124 (2020)
Cross-lingual entity linking (XEL) is the task of finding referents in a target-language knowledge base (KB) for mentions extracted from source-language texts. The first step of (X)EL is candidate generation, which retrieves a list of plausible candi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c561199f7040c70922d9bd083ce3efd9
http://arxiv.org/abs/2003.01343
http://arxiv.org/abs/2003.01343
Publikováno v:
EMNLP (1)
Modern NLP defines the task of style transfer as modifying the style of a given sentence without appreciably changing its semantics, which implies that the outputs of style transfer systems should be paraphrases of their inputs. However, many existin
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::aaf3ed1e2297f1b82efdcbfc13ffb042
Publikováno v:
EMNLP (1)
Semantic sentence embedding models encode natural language sentences into vectors, such that closeness in embedding space indicates closeness in the semantics between the sentences. Bilingual data offers a useful signal for learning such embeddings:
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6cd92fc32d763099b0e82d348f0f244a
https://doi.org/10.18653/v1/2020.emnlp-main.122
https://doi.org/10.18653/v1/2020.emnlp-main.122
Publikováno v:
ACL (1)
While most neural machine translation (NMT)systems are still trained using maximum likelihood estimation, recent work has demonstrated that optimizing systems to directly improve evaluation metrics such as BLEU can significantly improve final transla
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::57fcefb5364b5be0155731e07b42add7
https://doi.org/10.18653/v1/p19-1427
https://doi.org/10.18653/v1/p19-1427
Autor:
Kevin Gimpel, John Wieting
Publikováno v:
ACL (1)
We describe PARANMT-50M, a dataset of more than 50 million English-English sentential paraphrase pairs. We generated the pairs automatically by using neural machine translation to translate the non-English side of a large parallel corpus, following W
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9fc91ee920d1e6221ecb6d855a1f1e20
https://doi.org/10.18653/v1/p18-1042
https://doi.org/10.18653/v1/p18-1042
Publikováno v:
SEM@NAACL-HLT
We study the problem of measuring the quality of automatically-generated stories. We focus on the setting in which a few sentences of a story are provided and the task is to generate the next sentence (“continuation”) in the story. We seek to ide
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3cc53c17f78345fdff92617634542645
https://doi.org/10.18653/v1/s18-2024
https://doi.org/10.18653/v1/s18-2024
Publikováno v:
NAACL-HLT
We propose syntactically controlled paraphrase networks (SCPNs) and use them to generate adversarial examples. Given a sentence and a target syntactic form (e.g., a constituency parse), SCPNs are trained to produce a paraphrase of the sentence with t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7425354ef84d068b046a0192e503b453
https://doi.org/10.18653/v1/n18-1170
https://doi.org/10.18653/v1/n18-1170
Publikováno v:
Transactions of the Association for Computational Linguistics. 3:345-358
The Paraphrase Database (PPDB; Ganitkevitch et al., 2013) is an extensive semantic resource, consisting of a list of phrase pairs with (heuristic) confidence estimates. However, it is still unclear how it can best be used, due to the heuristic nature
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e8186bd63e6daf7d6305647976307fcd
https://doi.org/10.1162/tacl_a_00143
https://doi.org/10.1162/tacl_a_00143