SRL-Based Verb Selection for ESL

In this paper we develop an approach to tackle the problem of verb selection for learners of English as a second language (ESL) by using features from the output of Semantic Role Labeling (SRL). Unlike existing approaches to verb selection that use local features such as n-grams, our approach exploits semantic features which explicitly model the usage context of the verb. The verb choice highly depends on its usage context which is not consistently captured by local features. We then combine these semantic features with other local features under the generalized perceptron learning framework. Experiments on both indomain and out-of-domain corpora show that our approach outperforms the baseline and achieves state-of-the-art performance.1

• Type: Journal
• Year: 2010
• Where: EMNLP
• Authors: Xiaohua Liu, Bo Han, Kuan Li, Stephan Hyeonjun Stiller, Ming Zhou
• Keywords: EMNLP 2010, Local Features, Natural Language Processing, Semantic Features, Usage Context