Format du dépôt |
Fichier |
Type de dépôt |
Communication dans un congrès |
Titre |
en
SSP-based construction of evaluation-annotated data for fine-grained aspect-based sentiment analysis
|
Résumé |
en
We report the construction of a Korean evaluation-annotated corpus, hereafter called 'Evaluation Annotated Dataset (EVAD)', and its use in Aspect-Based Sentiment Analysis (ABSA) extended in order to cover e-commerce reviews containing sentiment and non-sentiment linguistic patterns. The annotation process uses Semi-Automatic Symbolic Propagation (SSP). We built extensive linguistic resources formalized as a Finite-State Transducer (FST) to annotate corpora with detailed ABSA components in the fashion e-commerce domain. The ABSA approach is extended, in order to analyze user opinions more accurately and extract more detailed features of targets, by including aspect values in addition to topics and aspects, and by classifying aspectvalue pairs depending whether values are unary, binary, or multiple. For evaluation, the KoBERT and KcBERT models are trained on the annotated dataset, showing robust performances of F1 0.88 and F1 0.90, respectively, on recognition of aspect-value pairs.
|
Auteur(s)
|
Suwon Choi
1, 2
, Shinwoo Kim
1, 2
, Changhoe Hwang
1, 2
, Gwanghoon Yoo
1, 2
, Eric Laporte
3
, Jeesun Nam
1, 2
1
DICORA -
Digital Language & Knowledge Contents Research Association
( 48744 )
- Room #315 Bat. Humanities & Social Science Hankuk University Of Foreign Studies, MOHYUN YONGIN-SI KYUNGGI-DO 449-791 KOREA
- Corée du Sud
-
Hankuk University of Foreign Studies ( 228654 )
2
HUFS -
Hankuk University of Foreign Studies
( 228654 )
- 81 Oedae-ro, Mohyeon-myeon, Cheoin-gu,Yongin-si, Gyeongi-do, 17035
- Corée du Sud
3
LIGM -
Laboratoire d'Informatique Gaspard-Monge
( 1001627 )
- Université Gustave Eiffel, Cité Descartes, Bâtiment Copernic, 5 bd Descartes, 77454 Marne-la-Vallée Cedex 2
- France
-
École des Ponts ParisTech ( 301545 )
;
-
Centre National de la Recherche Scientifique UMR8049 ( 441569 )
;
-
Université Gustave Eiffel ( 580722 )
|
URL du congrès ou éditeur |
https://aclanthology.org/volumes/2022.pandl-1/
|
Source |
COLING
|
Actes |
Oui
|
Titre de la collection |
Proceedings of the First Workshop on Pattern-based Approaches to NLP in the Age of Deep Learning
|
Volume |
29
|
Numéro |
1
|
Langue du document |
Anglais
|
Licence |
Paternité
|
Vulgarisation |
Non
|
Comité de lecture |
Oui
|
Invité |
Non
|
Audience |
Internationale
|
Date de publication |
2022
|
Page/Identifiant |
38-44
|
Titre du congrès |
29th International Conference on Computational Linguistics (COLING). Workshop on Pattern-based Approaches to NLP in the Age of Deep Learning (Pan-DL)
|
Date début congrès |
2022-10-12
|
Date fin congrès |
2022-10-17
|
Ville |
Gyeongju
|
Pays |
Corée du Sud
|
Domaine(s) |
-
Informatique [cs]/Informatique et langage [cs.CL]
-
Informatique [cs]/Traitement du texte et du document
-
Sciences de l'Homme et Société/Linguistique
|
Éditeur commercial |
-
International Committee on Computational Linguistics
|
Mots-clés |
en
Korean, Annotated Corpus, Annotated Dataset, Aspect-Based Sentiment Analysis, Semi-automatic Symbolic Propagation, Local Grammar Graph, Dictionary for language processing, E-dictionary, Unitex, Deep learning, Multiword Expression, MWE
|