Abstract
AbstractWe 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.
Highlights
NLP tasks such as morphological segmentation, morpheme tagging, part-of-speech (POS) tagging, and syntactic parsing onto semantic dependencies have been widely investigated for extracting the meaning of a clause
Our framework is built upon the joint POS tagging and dependency parsing model of Nguyen and Verspoor (2018), to which we introduce two more layers for morphological segmentation and morphological tagging
We excluded the morphological segmentation layer from the joint model for these experiments, since gold morphological segmentations are not available for these languages; only morphological tags are available in UD treebanks
Summary
NLP tasks such as morphological segmentation, morpheme tagging, part-of-speech (POS) tagging, and syntactic parsing onto semantic dependencies have been widely investigated for extracting the meaning of a clause These tasks can be considered to be different stages in reaching semantics: morphological segmentation and morpheme tagging deal with the morphemes inside a word;a POS tagging captures the words in a particular context, usually in a clause; dependency parsing views each clause as a sequence of words and the relations between them, such as subject, modifier, complement. In these tasks, morpheme tagging labels each morpheme in a word with the syntactic information of the morpheme in that particular context, for example, person or tense. Dependency labeling assigns a tag (e.g., subject, object, and modifier) to every dependency relation
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.