Zobrazeno 1 - 10
of 214
pro vyhledávání: '"PropBank"'
Autor:
Hyeong-gang Choe
Publikováno v:
Korean Linguistics. 88:247-273
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a464ca267be55b299b990ac8e29c2e51
https://doi.org/10.20405/kl.2020.08.88.247
https://doi.org/10.20405/kl.2020.08.88.247
Autor:
Claire Bonial, Kimberly A. Pollard
Publikováno v:
Journal of Linguistics. 56:577-600
Light verb constructions (LVCs) in English and Romance languages are somewhat unique crosslinguistically because LVCs in these languages tend to have semantically similar synthetic verb counterparts (Zarco 1999): e.g. make an appearance and appear. T
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f07990cbc2ca5213c8269be981346501
https://doi.org/10.1017/s0022226720000109
https://doi.org/10.1017/s0022226720000109
Autor:
Xue, Nianwen
Publikováno v:
Language Resources and Evaluation, 2006 Dec 01. 40(3/4), 395-403.
Externí odkaz:
https://www.jstor.org/stable/30208390
Publikováno v:
Lecture Notes in Networks and Systems ISBN: 9783030900540
In this article state of the art semantic role labeling (SRL) tools have been compared on published lexical resources and custom hand annotated previously unseen texts. Semantic role labeling is one of the first steps into understanding the meaning o
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::fca520b888b94a065838ea82d6764478
https://doi.org/10.1007/978-3-030-90055-7_16
https://doi.org/10.1007/978-3-030-90055-7_16
Publikováno v:
Applied Sciences
Volume 11
Issue 20
Applied Sciences, Vol 11, Iss 9423, p 9423 (2021)
Volume 11
Issue 20
Applied Sciences, Vol 11, Iss 9423, p 9423 (2021)
This paper presents a new method for semantic parsing with upper ontologies using FrameNet annotations and BERT-based sentence context distributed representations. The proposed method leverages WordNet upper ontology mapping and PropBank-style semant
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c8442dd11a7b8ddffeb0fdef477c81b1
Publikováno v:
Scopus-Elsevier
In this paper, we present and explain TRopBank “Turkish PropBank v2.0”. PropBank is a hand-annotated corpus of propositions which is used to obtain the predicate-argument information of a language. Predicate-argument information of a language can
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::7d01544267d9b9caac601efaba6facf3
https://hdl.handle.net/11729/2985
https://hdl.handle.net/11729/2985
Autor:
Minhua Huang, Robert M. Haralick
Publikováno v:
Pattern Recognition Letters. 124:21-30
We discuss a more powerful probabilistic graphical model for discovering semantic patterns from sequential text data, such as sentences. It is developed based on the idea that each word (or each symbol) in a sentence itself might carry lexical, seman
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ab48bcd392cf4d2192248640d33c56b8
https://doi.org/10.1016/j.patrec.2018.03.008
https://doi.org/10.1016/j.patrec.2018.03.008
Publikováno v:
Proceedings of the 5th Workshop on Structured Prediction for NLP (SPNLP 2021).
In this work, we empirically compare span extraction methods for the task of semantic role labeling (SRL). While recent progress incorporating pre-trained contextualized representations into neural encoders has greatly improved SRL F1 performance on
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::93f6156be1720d0defaca5c86f4cb153
https://doi.org/10.18653/v1/2021.spnlp-1.8
https://doi.org/10.18653/v1/2021.spnlp-1.8
Publikováno v:
NAACL-HLT
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
While cross-lingual techniques are finding increasing success in a wide range of Natural Language Processing tasks, their application to Semantic Role Labeling (SRL) has been strongly limited by the fact that each language adopts its own linguistic f
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3cbeaa57eab5c121213c5f7dc6232bcc
https://doi.org/10.18653/v1/2021.naacl-main.31
https://doi.org/10.18653/v1/2021.naacl-main.31
Publikováno v:
ACL/IJCNLP (Findings)
Contextualized word representations have proven useful for various natural language processing tasks. However, it remains unclear to what extent these representations can cover hand-coded semantic information such as semantic frames, which specify th
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::20f67a59842cb8e70c2afb6e30512b52