K. Erk and S. Pado: A Structured Vector Space Model for Word Meaning in Context. Proceedings of EMNLP-08, Honolulu, Hawai'i.
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 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.
@InProceedings{erk08:_struc_vector_space_model_word_meanin_contex,
author = {Katrin Erk and Sebastian Pad\'o},
title = {A Structured Vector Space Model for Word Meaning in Context},
booktitle = {Proceedings of EMNLP},
year = 2008,
address = {Honolulu, HI},
note = {To appear}
}