A Structured Vector Space Model for Word Meaning in Context

We address the task of computing vector space representations for the meaning of word occurrences, which can vary widely according to context. This task is a crucial step towards a robust, vector-based compositional account of sentence meaning. We argue that existing models for this task do not take syntactic structure sufficiently into account. We present a novel structured vector space model that addresses these issues by incorporating the selectional preferences for words' argument positions. This makes it possible to integrate syntax into the computation of word meaning in context. In addition, the model performs at and above the state of the art for modeling the contextual adequacy of paraphrases.

• Type: Conference
• Year: 2008
• Where: EMNLP
• Authors: Katrin Erk, Sebastian Padó
• Keywords: EMNLP 2008, Natural Language Processing, Vector Space, Vector Space Representations, Vector-based Compositional Account