A Walk-based Semantically Enriched Tree Kernel Over Distributed Word Representations

TY - GEN

T1 - A Walk-based Semantically Enriched Tree Kernel Over Distributed Word Representations

AU - Srivastava, Shashank

AU - Hovy, Dirk

PY - 2013

Y1 - 2013

N2 - In this paper, we propose a walk-based graph kernel that generalizes the notion of treekernels to continuous spaces. Our proposed approach subsumes a general framework for word-similarity, and in particular, provides a flexible way to incorporate distributed representations. Using vector representations, such an approach captures both distributional semantic similarities among words as well as the structural relations between them (encoded as the structure of the parse tree). We show an efficient formulation to compute this kernel using simple matrix operations. We present our results on three diverse NLP tasks, showing state-of-the-art results.

AB - In this paper, we propose a walk-based graph kernel that generalizes the notion of treekernels to continuous spaces. Our proposed approach subsumes a general framework for word-similarity, and in particular, provides a flexible way to incorporate distributed representations. Using vector representations, such an approach captures both distributional semantic similarities among words as well as the structural relations between them (encoded as the structure of the parse tree). We show an efficient formulation to compute this kernel using simple matrix operations. We present our results on three diverse NLP tasks, showing state-of-the-art results.

M3 - Article in proceedings

SP - 1411

EP - 1416

BT - Proceedings of EMNLP 2013

PB - Association for Computational Linguistics

ER -