Using morpheme-level attention mechanism for Turkish sequence labelling

With deep learning being used in natural language processing problems, there have been serious improvements in the solution of many problems in this area. Sequence labeling is one of these problems. In this study, we examine the effects of character, morpheme, and word representations on sequence labelling problems by proposing a model for the Turkish language by using deep neural networks. Modeling the word as a whole in agglutinative languages such as Turkish causes sparsity problem. Therefore, rather than handling the word as a whole, expressing a word through its characters or considering the morpheme and morpheme label information gives more detailed information about the word and mitigates the sparsity problem. In this study, we applied the existing deep learning models using different word or sub-word representations for Named Entity Recognition (NER) and Part-of-Speech Tagging (POS Tagging) in Turkish. The results show that using morpheme information of words improves the Turkish sequence labelling.

Citation

Eşref, Y. and Can, B. (2019) Using morpheme-level attention mechanism for Turkish sequence labelling, 2019 27th Signal Processing and Communications Applications Conference (SIU), 24-26 April 2019, Sivas, Turkey.

Type

Conference contribution

Language

other

Description

This is an accepted manuscript of an article published by IEEE in 2019 27th Signal Processing and Communications Applications Conference (SIU) on 22/08/2019, available online: https://ieeexplore.ieee.org/document/8806530 The accepted version of the publication may differ from the final published version.

ISSN

2165-0608

Collections

Research Institute in Information and Language Processing