Zobrazeno 1 - 10
of 94
pro vyhledávání: '"Lluís Màrquez"'
Publikováno v:
Computational Linguistics, Vol 43, Iss 4 (2017)
In this article, we explore the potential of using sentence-level discourse structure for machine translation evaluation. We first design discourse-aware similarity measures, which use all-subtree kernels to compare discourse parse trees in accordanc
Externí odkaz:
https://doaj.org/article/6a2f0f06540341fc95a08ea72c3d2142
Publikováno v:
Natural Language Engineering. 25:5-41
We analyze resources and models for Arabic community Question Answering (cQA). In particular, we focus on CQA-MD, our cQA corpus for Arabic in the domain of medical forums. We describe the corpus and the main challenges it poses due to its mix of inf
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::00d0c2df9a53882b905e91977837d7c9
https://doi.org/10.1017/s1351324918000426
https://doi.org/10.1017/s1351324918000426
We propose an automatic language-independent graph-based method to build \`a-la-carte article collections on user-defined domains from the Wikipedia. The core model is based on the exploration of the encyclopaedia's category graph and can produce bot
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::88847bdc13bc549681ef64ff9c72c6c2
http://arxiv.org/abs/2005.01177
http://arxiv.org/abs/2005.01177
Autor:
Preslav Nakov, Georgi Georgiev, Ivan Koychev, Lluís Màrquez, Tsvetomila Mihaylova, Todor Mihaylov
Publikováno v:
Internet Research. 28:1292-1312
Purpose The purpose of this paper is to explore the dark side of news community forums: the proliferation of opinion manipulation trolls. In particular, it explores the idea that a user who is called a troll by several people is likely to be one. It
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3d7f866d975dca43495e8b0edcfe93ed
https://doi.org/10.1108/intr-03-2017-0118
https://doi.org/10.1108/intr-03-2017-0118
Publikováno v:
Computational Linguistics. 43:683-722
In this article, we explore the potential of using sentence-level discourse structure for machine translation evaluation. We first design discourse-aware similarity measures, which use all-subtree kernels to compare discourse parse trees in accordanc
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8fcad058e4353232f87d1288c8434565
https://doi.org/10.1162/coli_a_00298
https://doi.org/10.1162/coli_a_00298
Publikováno v:
Prague Bulletin of Mathematical Linguistics, Vol 108, Iss 1, Pp 85-96 (2017)
We integrate new mechanisms in a document-level machine translation decoder to improve the lexical consistency of document translations. First, we develop a document-level feature designed to score the lexical consistency of a translation. This featu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bf4963906b252d9d87727e7e45a2d1c5
https://doi.org/10.1515/pralin-2017-0011
https://doi.org/10.1515/pralin-2017-0011
Publikováno v:
WMT@ACL
We present novel automatic metrics for machine translation evaluation that use discourse structure and convolution kernels to compare the discourse tree of an automatic translation with that of the human reference. We experiment with five transformat
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::75242cf8f3a961ecfcefc827396c695c
http://arxiv.org/abs/1911.12547
http://arxiv.org/abs/1911.12547
Autor:
Lluís Màrquez, Tsvetomila Mihaylova, Georgi Karadzhov, Pepa Atanasova, James Glass, Mitra Mohtarami, Alberto Barrón-Cedeño, Preslav Nakov
We study the problem of automatic fact-checking, paying special attention to the impact of contextual and discourse information. We address two related tasks: (i) detecting check-worthy claims, and (ii) fact-checking claims. We develop supervised sys
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b9c53a9e3800c7c2db1cc40698fe2585
http://arxiv.org/abs/1908.01328
http://arxiv.org/abs/1908.01328
Autor:
Karin Verspoor, Alessandro Moschitti, Preslav Nakov, Timothy Baldwin, Doris Hoogeveen, Lluís Màrquez, Hamdy Mubarak
Publikováno v:
SemEval@ACL
We describe SemEval-2017 Task 3 on Community Question Answering. This year, we reran the four subtasks from SemEval-2016:(A) Question-Comment Similarity,(B) Question-Question Similarity,(C) Question-External Comment Similarity, and (D) Rerank the cor
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b1b53bf95d90c17a644c280bc87e45cb
Publikováno v:
MRQA@EMNLP
We present a system for answering questions based on the full text of books (BookQA), which first selects book passages given a question at hand, and then uses a memory network to reason and predict an answer. To improve generalization, we pretrain o
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4421078bfd1fe0c97b05d2bd5fbf2f71
https://doi.org/10.18653/v1/d19-5811
https://doi.org/10.18653/v1/d19-5811