1 |
Exploitation du corpus Democrat par apprentissage artificiel
|
|
|
|
In: ISSN: 0458-726X ; EISSN: 1958-9549 ; Langages ; https://hal.archives-ouvertes.fr/hal-03475070 ; Langages, Armand Colin (Larousse jusqu'en 2003), 2021, Un corpus annoté en chaînes de référence et son exploitation– le projet Democrat, 224 (2021)
|
|
BASE
|
|
Show details
|
|
2 |
PUZZLING REFLEXIVE KENDI IN TURKISH AND ITS IMPLICATIONS FOR THE PARSER
|
|
|
|
BASE
|
|
Show details
|
|
3 |
Investigating query expansion and coreference resolution in question answering on BERT
|
|
|
|
In: Bhattacharjee, Santanu, Haque, Rejwanul orcid:0000-0003-1680-0099 , Maillette de Buy Wenniger, Gideon and Way, Andy orcid:0000-0001-5736-5930 (2020) Investigating query expansion and coreference resolution in question answering on BERT. In: 25th International Conference on Natural Language & Information Systems (NLDB 2020)), 24 - 26 June 2020, Saarbrücken, Germany (Online). ISBN 978-3-030-51309-2 (2020)
|
|
Abstract:
The Bidirectional Encoder Representations from Transformers (BERT) model produces state-of-the-art results in many question answering (QA) datasets, including the Stanford Question Answering Dataset (SQuAD). This paper presents a query expansion (QE) method that identifies good terms from input questions, extracts synonyms for the good terms using a widely-used language resource, WordNet, and selects the most relevant synonyms from the list of extracted synonyms. The paper also introduces a novel QE method that produces many alternative sequences for a given input question using same-language machine translation (MT). Furthermore, we use a coreference resolution (CR) technique to identify anaphors or cataphors in paragraphs and substitute them with the original referents. We found that the QA system with this simple CR technique significantly outperforms the BERT baseline in a QA task. We also found that our best-performing QA system is the one that applies these three preprocessing methods (two QE and CR methods) together to BERT, which produces an excellent F 1 score (89.8 F1 points) in a QA task. Further, we present a comparative analysis on the performances of the BERT QA models taking a variety of criteria into account, and demonstrate our findings in the answer span prediction task.
|
|
Keyword:
Computational linguistics; Computer engineering; coreference resolution; Information retrieval; Machine learning; Machine translating; machine translation; neural machine translation; query expansion; question answering
|
|
URL: http://doras.dcu.ie/24561/
|
|
BASE
|
|
Hide details
|
|
4 |
French coreference for spoken and written language
|
|
|
|
In: Language Resources and Evaluation Conference (LREC 2020) ; https://hal.archives-ouvertes.fr/hal-02476902 ; Language Resources and Evaluation Conference (LREC 2020), 2020, Marseille, France. pp.80-89 ; https://www.aclweb.org/anthology/2020.lrec-1.10 (2020)
|
|
BASE
|
|
Show details
|
|
5 |
Résolution d'anaphores nominales avec les séparateurs à vastes marges sur les arbres syntaxiques
|
|
|
|
In: CARI 2020 - Colloque Africain sur la Recherche en Informatique et en Mathématiques Appliquées ; https://hal.archives-ouvertes.fr/hal-02926896 ; CARI 2020 - Colloque Africain sur la Recherche en Informatique et en Mathématiques Appliquées, Oct 2020, Thiès, Sénégal (2020)
|
|
BASE
|
|
Show details
|
|
7 |
Prerequisites for Extracting Entity Relations from Swedish Texts
|
|
Lenas, Erik. - : KTH, Skolan för elektroteknik och datavetenskap (EECS), 2020
|
|
BASE
|
|
Show details
|
|
10 |
Extracting Global Entities Information from News
|
|
Xia, Chen. - : eScholarship, University of California, 2019
|
|
In: Xia, Chen. (2019). Extracting Global Entities Information from News. UCLA: Computer Science 0201. Retrieved from: http://www.escholarship.org/uc/item/0bv836gm (2019)
|
|
BASE
|
|
Show details
|
|
11 |
Slovene corpus for aspect-based sentiment analysis - SentiCoref 1.0
|
|
Žitnik, Slavko. - : Faculty of Computer and Information Science, University of Ljubljana, 2019
|
|
BASE
|
|
Show details
|
|
12 |
Classification par paires de mention pour la résolution des coréférences en français parlé interactif
|
|
|
|
In: Conférence jointe CORIA-TALN-RJC 2018 ; https://hal.inria.fr/hal-01821213 ; Conférence jointe CORIA-TALN-RJC 2018, ATALA; ARIA, May 2018, Rennes, France ; https://project.inria.fr/coriataln2018 (2018)
|
|
BASE
|
|
Show details
|
|
13 |
ParCorFull: A Parallel Corpus Annotated with Full Coreference
|
|
|
|
BASE
|
|
Show details
|
|
14 |
Slovene coreference resolution corpus coref149
|
|
Žitnik, Slavko. - : Faculty of Computer and Information Science, University of Ljubljana, 2018
|
|
BASE
|
|
Show details
|
|
15 |
Building effective representations for domain adaptation in coreference resolution
|
|
|
|
BASE
|
|
Show details
|
|
16 |
Coreference Resolution for Slovene on Annotated Data from coref149
|
|
|
|
In: Slovenščina 2.0: Empirične, aplikativne in interdisciplinarne raziskave, Vol 6, Iss 1, Pp 37-67 (2018) (2018)
|
|
BASE
|
|
Show details
|
|
17 |
Possession type affects resolution of possessive pronouns in English VP ellipsis
|
|
|
|
In: Proceedings of the Linguistic Society of America; Vol 3 (2018): Proceedings of the Linguistic Society of America; 52:1–14 ; 2473-8689 (2018)
|
|
BASE
|
|
Show details
|
|
20 |
Identifying and Resolving Entities in Text
|
|
|
|
In: Durrett, Gregory Christopher. (2016). Identifying and Resolving Entities in Text. UC Berkeley: Computer Science. Retrieved from: http://www.escholarship.org/uc/item/97t0811k (2016)
|
|
BASE
|
|
Show details
|
|
|
|