Language-Independent Approach for Morphological Disambiguation
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F22%3ASH9DW6S4" target="_blank" >RIV/00216208:11320/22:SH9DW6S4 - isvavai.cz</a>
Result on the web
<a href="https://aclanthology.org/2022.coling-1.470" target="_blank" >https://aclanthology.org/2022.coling-1.470</a>
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
Language-Independent Approach for Morphological Disambiguation
Original language description
This paper presents a language-independent approach for morphological disambiguation which has been regarded as an extension of POS tagging, jointly predicting complex morphological tags. In the proposed approach, all words, roots, POS and morpheme tags are embedded into vectors, and contexts representations from surface word and morphological contexts are calculated. Then the inner products between analyses and the context's representations are computed to perform the disambiguation. The underlying hypothesis is that the correct morphological analysis should be closer to the context in a vector space. Experimental results show that the proposed approach outperforms the existing models on seven different language datasets. Concretely, compared with the baselines of MarMot and a sophisticated neural model (Seq2Seq), the proposed approach achieves around 6% improvement in average accuracy for all languages while running about 6 and 33 times faster than MarMot and Seq2Seq, respectively.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
—
Continuities
—
Others
Publication year
2022
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Proceedings of the 29th International Conference on Computational Linguistics
ISBN
—
ISSN
2951-2093
e-ISSN
—
Number of pages
10
Pages from-to
5288-5297
Publisher name
International Committee on Computational Linguistics
Place of publication
—
Event location
Gyeongju, Republic of Korea
Event date
Jan 1, 2022
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—