Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Klim Zaporojets"'
Publikováno v:
APPLIED INTELLIGENCE
This work presents a new dialog dataset, CookDial, that facilitates research on task-oriented dialog systems with procedural knowledge understanding. The corpus contains 260 human-to-human task-oriented dialogs in which an agent, given a recipe docum
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f061ddca4cf870cd626d491f2e632272
https://doi.org/10.1007/s10489-022-03692-0
https://doi.org/10.1007/s10489-022-03692-0
Publikováno v:
PROCEEDINGS OF THE 60TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2022) : (SHORT PAPERS), VOL 2
We consider the task of document-level entity linking (EL), where it is important to make consistent decisions for entity mentions over the full document jointly. We aim to leverage explicit "connections" among mentions within the document itself: we
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8a43fe193c688be363515b15f04506f2
http://arxiv.org/abs/2108.13530
http://arxiv.org/abs/2108.13530
Publikováno v:
EXPERT SYSTEMS WITH APPLICATIONS
Solving arithmetic word problems is a cornerstone task in assessing language understanding and reasoning capabilities in NLP systems. Recent works use automatic extraction and ranking of candidate solution equations providing the answer to arithmetic
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ea1a19a00362308d3a62445585918999
https://biblio.ugent.be/publication/8715288
https://biblio.ugent.be/publication/8715288
Publikováno v:
ACL/IJCNLP (Findings)
Findings of the Association for Computational Linguistics : ACL-IJCNLP 2021
Findings of the Association for Computational Linguistics : ACL-IJCNLP 2021
We consider a joint information extraction (IE) model, solving named entity recognition, coreference resolution and relation extraction jointly over the whole document. In particular, we study how to inject information from a knowledge base (KB) in s
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::678b50182449e3986d06e78227eaee57
https://doi.org/10.18653/v1/2021.findings-acl.171
https://doi.org/10.18653/v1/2021.findings-acl.171
Publikováno v:
INFORMATION PROCESSING & MANAGEMENT
This paper presents DWIE, the ‘Deutsche Welle corpus for Information Extraction’, a newly created multi-task dataset that combines four main Information Extraction (IE) annotation subtasks: (i) Named Entity Recognition (NER), (ii) Coreference Res
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::69d8a11176ab01eb0638d0f280b944f4
Autor:
Giannis Bekoulis, Johannes Deleu, Chris Develder, Semere Kiros Bitew, Klim Zaporojets, Thomas Demeester, Lucas Sterckx
Publikováno v:
Proceedings of the Sixth Workshop on Computational Linguistics and Clinical Psychology.
This paper describes IDLab’s text classification systems submitted to Task A as part of the CLPsych 2019 shared task. The aim of this shared task was to develop automated systems that predict the degree of suicide risk of people based on their post
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::adbcfc4cfba511f82ab0cd00454c588b
https://doi.org/10.18653/v1/w19-3019
https://doi.org/10.18653/v1/w19-3019
Publikováno v:
CLPsych@NAACL-HTL
This paper describes the IDLab system submitted to Task A of the CLPsych 2018 shared task. The goal of this task is predicting psychological health of children based on language used in hand-written essays and socio-demographic control variables. Our
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::20f8747e2ee751922fdcee3c8d1afd12
https://biblio.ugent.be/publication/8567169/file/8567170
https://biblio.ugent.be/publication/8567169/file/8567170