A Hybrid Deep Dependency Parsing Approach Enhanced With Rules and Morphology: A Case Study for Turkish
Fully data-driven, deep learning-based models are usually designed as language-independent and have been shown to be successful for many natural language processing tasks. However, when the studied language is not high-resource and the amount of training data is insufficient, these models can benefi...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9869804/ |
| _version_ | 1811268242281332736 |
|---|---|
| author | Saziye Betul Ozates Arzucan Ozgur Tunga Gungor Balkiz Ozturk Basaran |
| author_facet | Saziye Betul Ozates Arzucan Ozgur Tunga Gungor Balkiz Ozturk Basaran |
| author_sort | Saziye Betul Ozates |
| collection | DOAJ |
| description | Fully data-driven, deep learning-based models are usually designed as language-independent and have been shown to be successful for many natural language processing tasks. However, when the studied language is not high-resource and the amount of training data is insufficient, these models can benefit from the integration of natural language grammar-based information. We propose two approaches to dependency parsing especially for languages with restricted amount of training data. Our first approach combines a state-of-the-art deep learning-based parser with a rule-based approach and the second one incorporates morphological information into the parser. In the rule-based approach, the parsing decisions made by the rules are encoded and concatenated with the vector representations of the input words as additional information to the deep network. The morphology-based approach proposes different methods to include the morphological structure of words into the parser network. Experiments are conducted on three different Turkish treebanks and the results suggest that integration of explicit knowledge about the target language to a neural parser through a rule-based parsing system and morphological analysis leads to more accurate annotations and hence, increases the parsing performance in terms of attachment scores. The proposed methods are developed for Turkish, but can be adapted to other languages as well. |
| first_indexed | 2024-04-12T21:18:18Z |
| format | Article |
| id | doaj.art-9030f909c82f49689d09074bb058bc74 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-12T21:18:18Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-9030f909c82f49689d09074bb058bc742022-12-22T03:16:23ZengIEEEIEEE Access2169-35362022-01-0110938679388610.1109/ACCESS.2022.32029479869804A Hybrid Deep Dependency Parsing Approach Enhanced With Rules and Morphology: A Case Study for TurkishSaziye Betul Ozates0https://orcid.org/0000-0003-3254-0960Arzucan Ozgur1Tunga Gungor2https://orcid.org/0000-0001-9448-9422Balkiz Ozturk Basaran3Department of Computer Engineering, Boğaziçi University, Bebek, İstanbul, TurkeyDepartment of Computer Engineering, Boğaziçi University, Bebek, İstanbul, TurkeyDepartment of Computer Engineering, Boğaziçi University, Bebek, İstanbul, TurkeyDepartment of Linguistics, Boğaziçi University, Bebek, İstanbul, TurkeyFully data-driven, deep learning-based models are usually designed as language-independent and have been shown to be successful for many natural language processing tasks. However, when the studied language is not high-resource and the amount of training data is insufficient, these models can benefit from the integration of natural language grammar-based information. We propose two approaches to dependency parsing especially for languages with restricted amount of training data. Our first approach combines a state-of-the-art deep learning-based parser with a rule-based approach and the second one incorporates morphological information into the parser. In the rule-based approach, the parsing decisions made by the rules are encoded and concatenated with the vector representations of the input words as additional information to the deep network. The morphology-based approach proposes different methods to include the morphological structure of words into the parser network. Experiments are conducted on three different Turkish treebanks and the results suggest that integration of explicit knowledge about the target language to a neural parser through a rule-based parsing system and morphological analysis leads to more accurate annotations and hence, increases the parsing performance in terms of attachment scores. The proposed methods are developed for Turkish, but can be adapted to other languages as well.https://ieeexplore.ieee.org/document/9869804/Dependency parsingcomputational linguisticsrecurrent neural networks |
| spellingShingle | Saziye Betul Ozates Arzucan Ozgur Tunga Gungor Balkiz Ozturk Basaran A Hybrid Deep Dependency Parsing Approach Enhanced With Rules and Morphology: A Case Study for Turkish IEEE Access Dependency parsing computational linguistics recurrent neural networks |
| title | A Hybrid Deep Dependency Parsing Approach Enhanced With Rules and Morphology: A Case Study for Turkish |
| title_full | A Hybrid Deep Dependency Parsing Approach Enhanced With Rules and Morphology: A Case Study for Turkish |
| title_fullStr | A Hybrid Deep Dependency Parsing Approach Enhanced With Rules and Morphology: A Case Study for Turkish |
| title_full_unstemmed | A Hybrid Deep Dependency Parsing Approach Enhanced With Rules and Morphology: A Case Study for Turkish |
| title_short | A Hybrid Deep Dependency Parsing Approach Enhanced With Rules and Morphology: A Case Study for Turkish |
| title_sort | hybrid deep dependency parsing approach enhanced with rules and morphology a case study for turkish |
| topic | Dependency parsing computational linguistics recurrent neural networks |
| url | https://ieeexplore.ieee.org/document/9869804/ |
| work_keys_str_mv | AT saziyebetulozates ahybriddeepdependencyparsingapproachenhancedwithrulesandmorphologyacasestudyforturkish AT arzucanozgur ahybriddeepdependencyparsingapproachenhancedwithrulesandmorphologyacasestudyforturkish AT tungagungor ahybriddeepdependencyparsingapproachenhancedwithrulesandmorphologyacasestudyforturkish AT balkizozturkbasaran ahybriddeepdependencyparsingapproachenhancedwithrulesandmorphologyacasestudyforturkish AT saziyebetulozates hybriddeepdependencyparsingapproachenhancedwithrulesandmorphologyacasestudyforturkish AT arzucanozgur hybriddeepdependencyparsingapproachenhancedwithrulesandmorphologyacasestudyforturkish AT tungagungor hybriddeepdependencyparsingapproachenhancedwithrulesandmorphologyacasestudyforturkish AT balkizozturkbasaran hybriddeepdependencyparsingapproachenhancedwithrulesandmorphologyacasestudyforturkish |