An Attempt to Develop a Neural Parser based on Simplified Head-Driven Phrase Structure Grammar on Vietnamese

2024-11-26

arXiv.org

AI Summary

This work addresses the problem that approximately 15% of constituent–dependency tree pairs in the Vietnamese treebanks VietTreebank and VnDT violate the constraints of simplified Head-Driven Phrase Structure Grammar (HPSG). We propose the first neural syntactic parser for Vietnamese grounded in simplified HPSG. Methodologically: (1) we design an automatic, linguist-free treebank correction strategy based on arc reordering to enhance grammatical consistency; (2) we integrate PhoBERT or XLM-RoBERTa into the simplified HPSG parsing framework. Experiments show our model achieves 82% constituent F-score on both treebanks—the state-of-the-art—while attaining significantly higher Unlabeled Attachment Score (UAS) than prior work; its slightly lower Labeled Attachment Score (LAS) stems from label-set mismatch, underscoring the need for linguistically informed annotation. This is the first end-to-end neural implementation of simplified HPSG for Vietnamese, establishing a new paradigm for grammar-consistent parsing in low-resource languages.

Technology Category

• Natural Language Processing: Syntax — Tagging, Chunking & Parsing
• Machine Learning: Neuro-Symbolic Learning
• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

In this paper, we aimed to develop a neural parser for Vietnamese based on simplified Head-Driven Phrase Structure Grammar (HPSG). The existing corpora, VietTreebank and VnDT, had around 15% of constituency and dependency tree pairs that did not adhere to simplified HPSG rules. To attempt to address the issue of the corpora not adhering to simplified HPSG rules, we randomly permuted samples from the training and development sets to make them compliant with simplified HPSG. We then modified the first simplified HPSG Neural Parser for the Penn Treebank by replacing it with the PhoBERT or XLM-RoBERTa models, which can encode Vietnamese texts. We conducted experiments on our modified VietTreebank and VnDT corpora. Our extensive experiments showed that the simplified HPSG Neural Parser achieved a new state-of-the-art F-score of 82% for constituency parsing when using the same predicted part-of-speech (POS) tags as the self-attentive constituency parser. Additionally, it outperformed previous studies in dependency parsing with a higher Unlabeled Attachment Score (UAS). However, our parser obtained lower Labeled Attachment Score (LAS) scores likely due to our focus on arc permutation without changing the original labels, as we did not consult with a linguistic expert. Lastly, the research findings of this paper suggest that simplified HPSG should be given more attention to linguistic expert when developing treebanks for Vietnamese natural language processing.

Problem

• Develop neural parser for Vietnamese using simplified HPSG
• Address non-compliance of corpora with simplified HPSG rules
• Improve Vietnamese parsing accuracy with modified neural models

Innovation

• Used simplified HPSG for Vietnamese neural parser
• Replaced models with PhoBERT or XLM-RoBERTa
• Permuted samples to adhere to HPSG rules