Modeling Composite Labels for Neural Morphological Tagging

Alexander Tkachenko, Kairit Sirts


Abstract
Neural morphological tagging has been regarded as an extension to POS tagging task, treating each morphological tag as a monolithic label and ignoring its internal structure. We propose to view morphological tags as composite labels and explicitly model their internal structure in a neural sequence tagger. For this, we explore three different neural architectures and compare their performance with both CRF and simple neural multiclass baselines. We evaluate our models on 49 languages and show that the neural architecture that models the morphological labels as sequences of morphological category values performs significantly better than both baselines establishing state-of-the-art results in morphological tagging for most languages.
Anthology ID:
K18-1036
Volume:
Proceedings of the 22nd Conference on Computational Natural Language Learning
Month:
October
Year:
2018
Address:
Brussels, Belgium
Editors:
Anna Korhonen, Ivan Titov
Venue:
CoNLL
SIG:
SIGNLL
Publisher:
Association for Computational Linguistics
Note:
Pages:
368–379
Language:
URL:
https://aclanthology.org/K18-1036
DOI:
10.18653/v1/K18-1036
Bibkey:
Cite (ACL):
Alexander Tkachenko and Kairit Sirts. 2018. Modeling Composite Labels for Neural Morphological Tagging. In Proceedings of the 22nd Conference on Computational Natural Language Learning, pages 368–379, Brussels, Belgium. Association for Computational Linguistics.
Cite (Informal):
Modeling Composite Labels for Neural Morphological Tagging (Tkachenko & Sirts, CoNLL 2018)
Copy Citation:
PDF:
https://aclanthology.org/K18-1036.pdf
Code
 AleksTk/seq-morph-tagger