Paper: A practical and linguistically-motivated approach to compositional distributional semantics

ACL ID P14-1009
Title A practical and linguistically-motivated approach to compositional distributional semantics
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2014
Authors

Distributional semantic methods to ap- proximate word meaning with context vectors have been very successful empir- ically, and the last years have seen a surge of interest in their compositional exten- sion to phrases and sentences. We present here a new model that, like those of Co- ecke et al. (2010) and Baroni and Zam- parelli (2010), closely mimics the standard Montagovian semantic treatment of com- position in distributional terms. However, our approach avoids a number of issues that have prevented the application of the earlier linguistically-motivated models to full-fledged, real-life sentences. We test the model on a variety of empirical tasks, showing that it consistently outperforms a set of competitive rivals. 1 Compositional distributional semantics The research of the last tw...