抽象语义表示解析方法研究综述

Survey on Abstract Meaning Representation Parsing

句子级语义分析是自然语言处理(NLP)的核心任务,面临复杂语义的表示问题。抽象语义表示(AMR)突破浅层局限,实现了领域无关的整句通用语义表示,具备准确表征句子完整语义的能力。因为AMR解析效果会影响下游NLP任务的表现,所以解析方法成为近年的国内外研究热点。由于时效性因素,既有AMR综述未涉及新涌现的解析方法,亟需深度聚焦其前沿文献。该文首先采用CiteSpace工具分析了AMR的总体研究情况。相比英文AMR解析研究,中文AMR解析研究成果数量相对较少,尚有较大的发展空间。进而分析了AMR语料库发展和AMR解析面临的概念和概念关系识别、对齐以及融入结构信息等问题。根据不同的解析策略将解析方法分为4类,以问题为驱动,剖析了各类AMR解析方法的演进。最后,选择21个英文AMR解析器、7个中文AMR解析器,比较分析Smatch等各项实验指标。归纳实验结果发现,现有模型在学习复杂多语义关系方面亟待加强。该文通过理论和实证分析为研究者提供AMR解析方法的发展脉络和研究思路。

Meaning Representation(AMR),with the ability of accurately abstracting the complete meaning of sentences,realizes domain-independent semantic representation of entire sentences.AMR parsing has an impact on the performance of downstream NLP tasks and becomes a popular research topic both domestically and internationally in recent years.We first employ the CiteSpace tool to analyze the overall research landscape of AMR,revealing a much less Chinese AMR parsing researches compared with those for English.Then we discuss the development of AMR corpus and the difficulties of concept recognition,relation recognition,alignment and integration of structural information in AMR parsing.We categorize AMR parsing into four types,and explore the evolution of AMR parsing methods.Finally,we select 21 English AMR parsers and 7 Chinese AMR parsers,and compare various experimental metrics including Smatch.