Thumbnail Image
Item

Joint learning of morphology and syntax with cross-level contextual information flow

Can Buglalilar, Burcu
; 
Alecakir, Huseyin
; 
Manandhar, Suresh
; 
Bozşahin, Cem
Authors
Can Buglalilar, Burcu
 Alecakir, Huseyin
 Manandhar, Suresh
 Bozşahin, Cem
Editors
Other contributors
Affiliation
Epub Date
Issue Date
2022-01-20
Submitted date
Subjects
dependency parsing
 attention
 recurrent neural networks
 morphological tagging
 morphological segmentation
 morphology
 syntax
 deep learning
Show all metadata
Files
Thumbnail Image
Can_et_al_Joint_learning_2021.pdf
Adobe PDF, 1.89 MB
Alternative
Abstract
We propose an integrated deep learning model for morphological segmentation, morpheme tagging, part-of-speech (POS) tagging, and syntactic parsing onto dependencies, using cross-level contextual information flow for every word, from segments to dependencies, with an attention mechanism at horizontal flow. Our model extends the work of Nguyen and Verspoor (2018) on joint POS tagging and dependency parsing to also include morphological segmentation and morphological tagging. We report our results on several languages. Primary focus is agglutination in morphology, in particular Turkish morphology, for which we demonstrate improved performance compared to models trained for individual tasks. Being one of the earlier efforts in joint modeling of syntax and morphology along with dependencies, we discuss prospective guidelines for future comparison.
Citation
Can, B., Aleçakır, H., Manandhar, S. and Bozşahin, C. (2022) Joint learning of morphology and syntax with cross-level contextual information flow. Natural Language Engineering, Can, B., Aleçakır, H., Manandhar, S., & Bozşahin, C. (2022). Joint learning of morphology and syntax with cross-level contextual information flow. Natural Language Engineering, 28(6), pp. 763-795. doi:10.1017/S1351324921000371
Publisher
Cambridge University Press
Journal
Natural Language Engineering
Research Unit
URI
http://hdl.handle.net/2436/624440
DOI
10.1017/S1351324921000371
PubMed ID
PubMed Central ID
Embedded videos
Additional Links
https://www.cambridge.org/core/journals/natural-language-engineering/article/joint-learning-of-morphology-and-syntax-with-crosslevel-contextual-information-flow/6D848C753AAA7DD978217645283F9DFE
Type
Journal article
Language
en
Description
© 2022 The Authors. Published by Cambridge University Press. This is an open access article available under a Creative Commons licence. The published version can be accessed at the following link on the publisher’s website: 10.1017/S1351324921000371
Series/Report no.
ISSN
1351-3249
EISSN
ISBN
ISMN
Gov't Doc #
Sponsors
This research has been supported by Scientific and Technological Research Council of Turkey (TUBITAK), project number EEEAG-115E464.
Rights
Research Projects
Organizational Units
Journal Issue
Embedded videos
Collections
Research Institute in Information and Language Processing