Cross-domain Chinese Sentence Pattern Parsing
This addresses a domain-specific issue for language teaching applications, but it is incremental as it builds on existing self-training and LLM methods.
The paper tackled the problem of cross-domain sentence pattern structure parsing in Chinese, which lacked adaptability due to reliance on textbook corpora, and achieved a 1.68-point improvement in F1 score over rule-based baselines.
Sentence Pattern Structure (SPS) parsing is a syntactic analysis method primarily employed in language teaching.Existing SPS parsers rely heavily on textbook corpora for training, lacking cross-domain capability.To overcome this constraint, this paper proposes an innovative approach leveraging large language models (LLMs) within a self-training framework. Partial syntactic rules from a source domain are combined with target domain sentences to dynamically generate training data, enhancing the adaptability of the parser to diverse domains.Experiments conducted on textbook and news domains demonstrate the effectiveness of the proposed method, outperforming rule-based baselines by 1.68 points on F1 metrics.