Contextualizing Semantic Representations Using Syntactically Enriched Vector Models
Stefan Thater, Hagen Fuerstenau, and Manfred Pinkal
In: 48th Annual Meeting of the Association for Computational Linguistics, 11-16 July 2010, Uppsala, Sweden.
We present a syntactically enriched vector model that supports the computation
of contextualized semantic representations in a quasi compositional fashion.
It employs a systematic combination of first- and second-order context
vectors. We apply our model to two different tasks and show that (i) it
substantially outperforms previous work on a paraphrase ranking task, and
(ii) achieves promising results on a word-sense similarity task; to our
knowledge, it is the first time that an unsupervised method has been applied
to this task.