Zobrazeno 1 - 10
of 71
pro vyhledávání: '"Amir, Zeldes"'
Publikováno v:
Computational Linguistics (2024)
Externí odkaz:
https://doaj.org/article/48f34cd90d844fbcb26997c1cf805f7a
Autor:
Amir Zeldes
This book centers on the idea that some verbs and other argument structure constructions have an inherently different propensity to realize lexically unfamiliar arguments, independently of lexical semantic meaning. This notion is explored both qualit
Autor:
Caroline T. Schroeder, Amir Zeldes
Publikováno v:
Journal of Data Mining and Digital Humanities, Vol Special Issue on Collecting,... (2020)
Scholarship on underresourced languages bring with them a variety of challenges which make access to the full spectrum of source materials and their evaluation difficult. For Coptic in particular, large scale analyses and any kind of quantitative wor
Externí odkaz:
https://doaj.org/article/b736f748ee55448a9b890648287856ba
Autor:
Amir Zeldes
Publikováno v:
Dialogue & Discourse. 13:41-62
Current work on automatic coreference resolution has focused on the OntoNotes benchmark dataset, due to both its size and consistency. However many aspects of the OntoNotes annotation scheme are not well understood by NLP practitioners, including the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f6ca60d63e84b0e9b919d31f4dad5cd4
https://doi.org/10.5210/dad.2022.102
https://doi.org/10.5210/dad.2022.102
SOTA coreference resolution produces increasingly impressive scores on the OntoNotes benchmark. However lack of comparable data following the same scheme for more genres makes it difficult to evaluate generalizability to open domain data. Zhu et al.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d0aebfd60efad2419c772440b5f19f14
http://arxiv.org/abs/2110.05727
http://arxiv.org/abs/2110.05727
This paper describes our submission to the DISRPT2021 Shared Task on Discourse Unit Segmentation, Connective Detection, and Relation Classification. Our system, called DisCoDisCo, is a Transformer-based neural classifier which enhances contextualized
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::52d5443390400786e5574229c1b68eab
http://arxiv.org/abs/2109.09777
http://arxiv.org/abs/2109.09777
Publikováno v:
ACL/IJCNLP (2)
SOTA coreference resolution produces increasingly impressive scores on the OntoNotes benchmark. However lack of comparable data following the same scheme for more genres makes it difficult to evaluate generalizability to open domain data. This paper
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::fdfe912e84e8965415fcf39574d02727
http://arxiv.org/abs/2106.00933
http://arxiv.org/abs/2106.00933
Publikováno v:
Proceedings of the Fifth Workshop on Teaching NLP.
This paper describes the primarily-graduate computational linguistics and NLP curriculum at Georgetown University, a U.S. university that has seen significant growth in these areas in recent years. We reflect on the principles behind our curriculum c
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::49c4a7194da798b2a807bf6a51b603e8
https://doi.org/10.18653/v1/2021.teachingnlp-1.11
https://doi.org/10.18653/v1/2021.teachingnlp-1.11
Publikováno v:
Proceedings of the 2nd Shared Task on Discourse Relation Parsing and Treebanking (DISRPT 2021).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8b348ea878231a150e1e351a73ff4a6e
https://doi.org/10.18653/v1/2021.disrpt-1.1
https://doi.org/10.18653/v1/2021.disrpt-1.1
Autor:
Manuela Sanguinetti, Cristina Bosco, Lauren Cassidy, Özlem Çetinoğlu, Alessandra Teresa Cignarella, Teresa Lynn, Ines Rehbein, Josef Ruppenhofer, Djamé Seddah, Amir Zeldes
This article presents a discussion on the main linguistic phenomena which cause difficulties in the analysis of user-generated texts found on the web and in social media, and proposes a set of annotation guidelines for their treatment within the Univ
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::79d70d50a75432cf907c73f5a3b27c0f
http://arxiv.org/abs/2011.02063
http://arxiv.org/abs/2011.02063