arXiv:2503.18751cs.CLcs.AI2025-03被引 8

BERT能识别并区分英语中多义的名词+介词+名词结构

Construction Identification and Disambiguation Using BERT: A Case Study of NPN

  • 用标注数据集训练分类器探测BERT对NPN结构的表征
  • 分类准确率达78.3%,可区分构造与干扰项,实现语义消歧
  • 对词序敏感,说明其编码了形式与意义的深层关联

构式语法认为语言知识主要由形式-意义配对(构式)构成,包括词汇、通用语法规则甚至特殊模式。近期研究表明,变压器语言模型能表征部分构式,包括罕见构式。本文探究BERT对英语中一种小型但多义的构式——NPN(名词-介词-名词)——的形式与意义表征,如'face to face'和'day to day'。我们构建了一个带语义标注的语料库基准数据集(含外观相似的干扰项),并训练评估探测分类器。结果表明,该分类器在区分真实构造与干扰项上表现良好,准确率达78.3%;同时能实现真例间的语义消歧。人为打乱真实构式实例的词序后,模型将其判定为非构造,表明其对形式敏感。结论:BERT隐式编码了超越表面句法和词汇线索的NPN构式知识。

原文摘要 · Abstract (English)

Construction Grammar hypothesizes that knowledge of a language consists chiefly of knowledge of form-meaning pairs (''constructions'') that include vocabulary, general grammar rules, and even idiosyncratic patterns. Recent work has shown that transformer language models represent at least some constructional patterns, including ones where the construction is rare overall. In this work, we probe BERT's representation of the form and meaning of a minor construction of English, the NPN (noun-preposition-noun) construction -- exhibited in such expressions as face to face and day to day -- which is known to be polysemous. We construct a benchmark dataset of semantically annotated corpus instances (including distractors that superficially resemble the construction). With this dataset, we train and evaluate probing classifiers. They achieve decent discrimination of the construction from distractors, as well as sense disambiguation among true instances of the construction, revealing that BERT embeddings carry indications of the construction's semantics. Moreover, artificially permuting the word order of true construction instances causes them to be rejected, indicating sensitivity to matters of form. We conclude that BERT does latently encode at least some knowledge of the NPN construction going beyond a surface syntactic pattern and lexical cues.

BERT构式语法语义消歧语言模型

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。