用大模型反向生成跨领域句法树库，提升泛化解析能力。
Contrastive Learning on LLM Back Generation Treebank for Cross-domain Constituency Parsing
- 通过大模型反向填充关键词叶子节点生成跨域句法树
- 在MCTB五个领域上实现当前最优平均性能
- 适合需要低资源领域句法分析的研究者
跨领域句法解析仍是计算语言学中的未解难题，因多领域句法树库数据有限。本文探索利用大语言模型（LLMs）自动生成句法树库。由于LLMs在句法解析任务上表现不佳，我们提出一种新方法：LLM反向生成，其过程类似于句法解析的逆过程。该方法以仅含领域关键词叶子节点的不完整跨域句法树为输入，填充缺失词汇以生成完整的跨域句法树库。此外，我们还引入一种跨度级对比学习预训练策略，充分挖掘该树库在跨领域句法解析中的潜力。在MCTB五个目标领域的实验验证了该方法的有效性，结果表明，结合对比学习预训练的方案在平均性能上优于多种基线模型。
原文摘要 · Abstract (English)
Cross-domain constituency parsing is still an unsolved challenge in computational linguistics since the available multi-domain constituency treebank is limited. We investigate automatic treebank generation by large language models (LLMs) in this paper. The performance of LLMs on constituency parsing is poor, therefore we propose a novel treebank generation method, LLM back generation, which is similar to the reverse process of constituency parsing. LLM back generation takes the incomplete cross-domain constituency tree with only domain keyword leaf nodes as input and fills the missing words to generate the cross-domain constituency treebank. Besides, we also introduce a span-level contrastive learning pre-training strategy to make full use of the LLM back generation treebank for cross-domain constituency parsing. We verify the effectiveness of our LLM back generation treebank coupled with contrastive learning pre-training on five target domains of MCTB. Experimental results show that our approach achieves state-of-the-art performance on average results compared with various baselines.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。