Zobrazeno 1 - 10
of 18
pro vyhledávání: '"Lasha Abzianidze"'
Autor:
Malvina Nissim, Lasha Abzianidze, Kilian Evang, Rob van der Goot, Hessel Haagsma, Barbara Plank, Martijn Wieling
Publikováno v:
Computational Linguistics, Vol 43, Iss 4 (2017)
Externí odkaz:
https://doaj.org/article/125d96a890f14c72918b81255a9af221
Autor:
Lasha, Abzianidze, Johan, Bos
Publikováno v:
言語処理学会第26回年次大会発表論文集. :1145-1148
理化学研究所 / お茶の水女子大学
お茶の水女子大学
駿河台大学
東京大学
国立国語研究所
フローニンゲン大学
Institute of Physical and Chemical Research / Ochanomizu University
お茶の水女子大学
駿河台大学
東京大学
国立国語研究所
フローニンゲン大学
Institute of Physical and Chemical Research / Ochanomizu University
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=jairo_______::b259e16551f6378ea2c05d3751390c91
https://repository.ninjal.ac.jp/records/3076
https://repository.ninjal.ac.jp/records/3076
Publikováno v:
Transactions of the Association for Computational Linguistics, 6, 619-633. Association for Computational Linguistics (ACL)
Neural methods have had several recent successes in semantic parsing, though they have yet to face the challenge of producing meaning representations based on formal semantics. We present a sequence-to-sequence neural semantic parser that is able to
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5aba693b0ce10017ea895a6c486af490
https://doi.org/10.1162/tacl_a_00241
https://doi.org/10.1162/tacl_a_00241
Autor:
Johan Bos, Lasha Abzianidze
Meaning banking--creating a semantically annotated corpus for the purpose of semantic parsing or generation--is a challenging task. It is quite simple to come up with a complex meaning representation, but it is hard to design a simple meaning represe
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6760e19a6d376c62fe31c609f45e4097
Publikováno v:
Proceedings of the IWCS Shared Task on Semantic Parsing
The paper presents the IWCS 2019 shared task on semantic parsing where the goal is to produce Discourse Representation Structures (DRSs) for English sentences. DRSs originate from Discourse Representation Theory and represent scoped meaning represent
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d23356db5cba213d5a0dc2e7cef02b63
Autor:
Lasha Abzianidze, Malvina Nissim, Hessel Haagsma, Barbara Plank, Kilian Evang, Martijn Wieling, Rob van der Goot
Publikováno v:
Computational Linguistics, 43(4), 897-904. MIT Press
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c9a1f157f10d3b76e27670ab4db9bf74
https://doi.org/10.1162/coli_a_00304
https://doi.org/10.1162/coli_a_00304
Autor:
Koji Mineshima, Johan Bos, Daisuke Bekki, Satoshi Sekine, Hitomi Yanaka, Lasha Abzianidze, Kentaro Inui
Publikováno v:
BlackboxNLP@ACL
Monotonicity reasoning is one of the important reasoning skills for any intelligent natural language inference (NLI) model in that it requires the ability to capture the interaction between lexical and syntactic structures. Since no test set has been
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ff6081ce2f43889bbed3d54c58903e17
http://arxiv.org/abs/1906.06448
http://arxiv.org/abs/1906.06448
Publikováno v:
LAW@ACL
Proceedings of the 13th Linguistic Annotation Workshop
Proceedings of the 13th Linguistic Annotation Workshop
We present the first open-source graphical annotation tool for combinatory categorial grammar (CCG), and the first set of detailed guidelines for syntactic annotation with CCG, for four languages: English, German, Italian, and Dutch. We also release
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ec791f9d4bde115f14e9856d5f19975c
https://doi.org/10.18653/v1/w19-4005
https://doi.org/10.18653/v1/w19-4005
Autor:
Hitomi Yanaka, Daisuke Bekki, Johan Bos, Satoshi Sekine, Koji Mineshima, Kentaro Inui, Lasha Abzianidze
Publikováno v:
SEM@NAACL-HLT
Large crowdsourced datasets are widely used for training and evaluating neural models on natural language inference (NLI). Despite these efforts, neural models have a hard time capturing logical inferences, including those licensed by phrase replacem
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::971a9069d2706f766db342a6a92e9751
Publikováno v:
EMNLP
University of Groningen
2018 Conference on Empirical Methods in Natural Language Processing
University of Groningen
2018 Conference on Empirical Methods in Natural Language Processing
We investigate the effects of multi-task learning using the recently introduced task of semantic tagging. We employ semantic tagging as an auxiliary task for three different NLP tasks: part-of-speech tagging, Universal Dependency parsing, and Natural
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0d4ee698e9754757deb3de75debdb938
http://arxiv.org/abs/1808.09716
http://arxiv.org/abs/1808.09716