Prepositions in Context
Hongyu Gong, Jiaqi Mu, Suma Bhat, Pramod Viswanath Department of Electrical and Computer Engineering University of Illinois at Urbana Champaign, USA
Abstract
Prepositions are highly polysemous, and their variegated senses encode significant semantic information. In this paper we match each preposition’s complement and attachment and their interplay crucially to the geometry of the word vectors to the left and right of the preposition. Extracting such features from the vast number of instances of each preposition and clustering them makes for an efficient preposition sense disambigution (PSD) algorithm, which is comparable to and better than state-of-the-art on two benchmark datasets. Our reliance on no external linguistic resource allows us to scale the PSD algorithm to a large WikiCorpus and learn sense-specific preposition representations – which we show to encode semantic relations and paraphrasing of verb particle compounds, via simple vector operations.
中文速览
介词（preposition）高度多义，同一个词在不同语境下含义迥异，传统消歧方法离不开词性标注器、依存句法分析器等语言工具，难以大规模推广。本文提出一种仅依赖词向量的介词义项消歧（Preposition Sense Disambiguation, PSD）方法：将介词左侧上下文、右侧上下文以及二者"交互"的几何关系分别提取为三个特征向量，再通过聚类或分类器完成义项判别，无需任何外部语言资源。在SemEval 2007和OEC两个标准数据集上，该方法在无监督设置下比最优基线提升2.4%，在有监督设置下也达到或超越了同类最先进系统。更进一步，作者将消歧结果回标到大规模维基语料，为每个义项学习专属的介词向量表示，并发现这些表示能通过简单向量加法编码语义关系、辅助动词短语释义（如"fight for"→"defend"），揭示了介词中隐藏的丰富语义信息可被基本代数运算所利用。
原文 arXiv:1702.01466;中英对照 + 大白话阅读 https://aha.fim.ai/paper/1702.01466v1