Explicit and Implicit Syntactic Features for Text Classification
Matt Post and Shane Bergsma
The 51st Annual Meeting of the Association for Computational Linguistics - Short Papers (ACL Short Papers 2013)
Sofia, Bulgaria, August 4-9, 2013
Syntactic features are useful for many text classification tasks. Among these, tree kernels (Collins and Duffy, 2001) have been perhaps the most robust and effective syntactic tool, appealing for their empirical success reasons, but also because they do not require an answer to the difficult question of which tree features to use for a given task. In this paper, we compare tree kernels with various explicit tree feature sets on three tasks. In these settings, explicit features perform as well as tree kernels on accuracy measurements, but in orders of magnitude less time and model size. Since explicit features are easy to generate and use (with publicly available tools), we suggest they should always be included as baseline comparisons in tree kernel method evaluations.
Conference Manager (V2.61.0 - Rev. 2792M)