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


CAN BUĞLALILAR B., Alecakir H., Manandhar S., Bozsahin C.

NATURAL LANGUAGE ENGINEERING, vol.28, no.6, pp.763-795, 2022 (SCI-Expanded) identifier identifier

  • Publication Type: Article / Article
  • Volume: 28 Issue: 6
  • Publication Date: 2022
  • Doi Number: 10.1017/s1351324921000371
  • Journal Name: NATURAL LANGUAGE ENGINEERING
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Arts and Humanities Citation Index (AHCI), Social Sciences Citation Index (SSCI), Scopus, Applied Science & Technology Source, Compendex, Computer & Applied Sciences, INSPEC, Linguistics & Language Behavior Abstracts, Psycinfo, DIALNET
  • Page Numbers: pp.763-795
  • Keywords: Morphology, Syntax, Dependency parsing, Morphological tagging, Morphological segmentation, Recurrent neural networks, Attention
  • Middle East Technical University Affiliated: Yes

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). Proceedings of the CoNLL Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies. The Association for Computational Linguistics, pp. 81-91.) 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.