Improving a Neural-based Tagger for Multiword Expression Identification
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F18%3A10390216" target="_blank" >RIV/00216208:11320/18:10390216 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
Improving a Neural-based Tagger for Multiword Expression Identification
Original language description
In this paper, we present a set of improvements introduced to MUMULS, a tagger for the automatic detection of verbal multiword expressions. Our tagger participated in the PARSEME shared task and it was the only one based on neural networks. We show that character-level embeddings can improve the performance, mainly by reducing the out-of-vocabulary rate. Furthermore, replacing the softmax layer in the decoder by a conditional random field classifier brings additional improvements. Finally, we compare different context-aware feature representations of input tokens using various encoder architectures. The experiments on Czech show that the combination of character-level embeddings using a convolutional network, self-attentive encoding layer over the word representations and an output conditional random field classifier yields the best empirical results.
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
Result was created during the realization of more than one project. More information in the Projects tab.
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>S - Specificky vyzkum na vysokych skolach<br>I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace
Others
Publication year
2018
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 11th International Conference on Language Resources and Evaluation (LREC 2018)
ISBN
979-10-95546-00-9
ISSN
—
e-ISSN
neuvedeno
Number of pages
7
Pages from-to
2526-2532
Publisher name
European Language Resources Association
Place of publication
Paris, France
Event location
Miyazaki, Japan
Event date
May 7, 2018
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—