Zobrazeno 1 - 10
of 22
pro vyhledávání: '"Kohsuke Yanai"'
Publikováno v:
Transactions of the Association for Computational Linguistics. 10:639-658
Mining an argument structure from text is an important step for tasks such as argument search and summarization. While studies on argument(ation) mining have proposed promising neural network models, they usually suffer from a shortage of training da
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::07ee16d77d9a6b275892b34e10c58a45
https://doi.org/10.1162/tacl_a_00481
https://doi.org/10.1162/tacl_a_00481
Publikováno v:
ACL
State-of-the-art argument mining studies have advanced the techniques for predicting argument structures. However, the technology for capturing non-tree-structured arguments is still in its infancy. In this paper, we focus on non-tree argument mining
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::85837aeec69c41bf95ea06894d9c8626
https://doi.org/10.18653/v1/2020.acl-main.298
https://doi.org/10.18653/v1/2020.acl-main.298
Publikováno v:
Communications in Computer and Information Science ISBN: 9789811561672
PACLING
PACLING
Split-and-rephrase is a strategy known to be used when humans need to break down a complex sentence into a meaning preserving sequence of shorter ones. Recent work proposed to model split-and-rephrase as a supervised sequence generation problem. Howe
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::46614e0e7e553535e7f8124250ffdc4b
https://doi.org/10.1007/978-981-15-6168-9_2
https://doi.org/10.1007/978-981-15-6168-9_2
Publikováno v:
CoNLL Shared Task
This paper describes the proposed system of the Hitachi team for the Cross-Framework Meaning Representation Parsing (MRP 2019) shared task. In this shared task, the participating systems were asked to predict nodes, edges and their attributes for fiv
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::fd2ff34dae833f58dd379da54baaeffc
http://arxiv.org/abs/1910.01299
http://arxiv.org/abs/1910.01299
Autor:
Yuta Koreeda, Kohsuke Yanai, Takuya Hashito, Yoshiki Niwa, Sato Misa, Toshihiko Yanase, Kenzo Kurotsuchi
Publikováno v:
SemEval@ACL
This paper describes a text-ranking system developed by bunji team in SemEval-2017 Task 3: Community Question Answering, Subtask A and C. The goal of the task is to re-rank the comments in a question-and-answer forum such that useful comments for ans
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c0ad50d85d03d86bba4242b86fb38839
https://doi.org/10.18653/v1/s17-2058
https://doi.org/10.18653/v1/s17-2058
Publikováno v:
EMNLP (System Demonstrations)
We present a tool for developing tree structure patterns that makes it easy to define the relations among textual phrases and create a search index for these newly defined relations. By using the proposed tool, users develop tree structure patterns t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::bfa47c88a249d3502731071b86fd5db2
https://doi.org/10.18653/v1/d17-2006
https://doi.org/10.18653/v1/d17-2006
Publikováno v:
Transactions of the Japanese Society for Artificial Intelligence. 34:F-IC1_1
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::cb2dfff73ad35c8d2f96c0b11262e16e
https://doi.org/10.1527/tjsai.f-ic1
https://doi.org/10.1527/tjsai.f-ic1
Publikováno v:
SemEval@NAACL-HLT
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::538c15b2f5bf221bbb106beca76df841
https://doi.org/10.18653/v1/s16-1046
https://doi.org/10.18653/v1/s16-1046
Publikováno v:
ArgMining@ACL
Evidences that support a claim “a subject phrase promotes or suppresses a value” help in making a rational decision. We aim to construct a model that can classify if a particular evidence supports a claim of a promoting/suppressing relationship g
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b41accb524d575dfedf99e34deb56348
https://doi.org/10.18653/v1/w16-2809
https://doi.org/10.18653/v1/w16-2809
Publikováno v:
Transactions of the Japanese Society for Artificial Intelligence. 26:594-606
We propose a data processing platform that can analyze a large amount of tree-structured data. The proposed platform stores tree-structured data in separated files corresponding to each attribute, and uses MapReduce framework for distributed computin
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d44ee1500711e8a6cf93e62ad406fb5a
https://doi.org/10.1527/tjsai.26.594
https://doi.org/10.1527/tjsai.26.594