Summary of Cross-domain Chinese Sentence Pattern Parsing, by Jingsi Yu et al.
Cross-domain Chinese Sentence Pattern Parsing
by Jingsi Yu, Cunliang Kong, Liner Yang, Meishan Zhang, Lin Zhu, Yujie Wang, Haozhe Lin, Maosong Sun, Erhong Yang
First submitted to arxiv on: 26 Feb 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper proposes an innovative approach to overcome the constraint of relying on textbook corpora for training Sentence Pattern Structure (SPS) parsers. Leveraging large language models (LLMs), the method combines partial syntactic rules from a source domain with target domain sentences to dynamically generate training data, enhancing the parser’s adaptability to diverse domains. The proposed method is evaluated on both textbook and news domains, outperforming rule-based baselines by 1.68 points on F1 metrics. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper helps SPS parsers work better by using big language models. Right now, these parsers rely too much on textbooks, which limits their ability to understand different types of writing. To fix this, the authors combine small rules from one domain with sentences from another domain to create new training data. This makes the parser more flexible and able to learn from a wider variety of texts. |
