Multiword expressions processing in Galician using Deep Learning

被引：1

作者：

Darriba, Victor ^{[1
]}

Doval, Yerai ^{[1
]}

Kuriyozov, Elmurod ^{[2
]}

机构：

[1] Univ Vigo, Dept Informat, Vigo, Spain

[2] Univ A Coruna, CITIC, La Coruna, Spain

来源：

PROCESAMIENTO DEL LENGUAJE NATURAL | 2021年 / 67期

关键词：

Multiword expressions; machine learning; transformers; Galician;

D O I：

10.26342/2021-67-4

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Treatment of Multiword Expressions is still a pending task in Natural Language Processing. In this work, we want to experimentally determine the usefulness of Machine Learning models for Multiword Expression processing in Galician. With that aim, we use CORGA, a 40 million word corpus, with which we train Deep Learning-based transformers, comparing their performances with those of more traditional conditional random fields.

引用

页码：45 / 57

页数：13

共 50 条

[21] A QUANTITATIVE STUDY OF THE MORPHOLOGY OF ITALIAN MULTIWORD EXPRESSIONS
Nissim, Malvina
Zaninello, Andrea
LINGUE E LINGUAGGIO, 2011, 10 (02) : 283 - 299
[22] Modeling Semantic Compositionality of Croatian Multiword Expressions
Snajder, Jan
Almic, Petra
INFORMATICA-JOURNAL OF COMPUTING AND INFORMATICS, 2015, 39 (03): : 301 - 309
[23] Dictionary of Bulgarian Multiword Expressions - Advances and Prospects
Stoyanova, Ivelina
Todorova, Maria
Leseva, Svetlozara
PROCEEDINGS OF THE INTERNATIONAL JUBILEE CONFERENCE OF THE INSTITUTE FOR BULGARIAN LANGUAGE, VOL 1, 2017, : 311 - 320
[24] DuELME: a Dutch electronic lexicon of multiword expressions
Gregoire, Nicole
LANGUAGE RESOURCES AND EVALUATION, 2010, 44 (1-2) : 23 - 39
[25] Annotation of multiword expressions in the Prague dependency treebank
Eduard Bejček
Pavel Straňák
Language Resources and Evaluation, 2010, 44 : 7 - 21
[26] Analyzing and identifying multiword expressions in spoken language
Helmer Strik
Micha Hulsbosch
Catia Cucchiarini
Language Resources and Evaluation, 2010, 44 : 41 - 58
[27] A Romanian Treebank Annotated with Verbal Multiword Expressions
Mititelu, Verginica Barbu
Cristescu, Mihaela
Mitrofan, Maria
Zgreaban, Bianca-Madalina
Barbulescu, Elena-Andreea
PROCEEDINGS OF THE FIFTH INTERNATIONAL CONFERENCE COMPUTATIONAL LINGUISTICS IN BULGARIA, CLIB 2022, 2022, : 137 - 145
[28] DuELME: a Dutch electronic lexicon of multiword expressions
Nicole Grégoire
Language Resources and Evaluation, 2010, 44 : 23 - 39
[29] Alignment-based extraction of multiword expressions
Caseli, Helena de Medeiros
Ramisch, Carlos
Volpe Nunes, Maria das Gracas
Villavicencio, Aline
LANGUAGE RESOURCES AND EVALUATION, 2010, 44 (1-2) : 59 - 77
[30] A Corpus Study of Verbal Multiword Expressions in Brazilian Portuguese
Ramisch, Carlos
Ramisch, Renata
Zilio, Leonardo
Villavicencio, Aline
Cordeiro, Silvio
COMPUTATIONAL PROCESSING OF THE PORTUGUESE LANGUAGE, PROPOR 2018, 2018, 11122 : 24 - 34

← 1 2 3 4 5 →