2010 · 17 citations · 18 references
Language StudiesComputer ScienceEnglish As A Second LanguageComputational LinguisticsNatural Language ProcessingSecond Language LearningLanguage ModelingLearner CorporaSecond Language AcquisitionSemantic Role LabelingSyntactic AnalysisWritten CorporaContextPerceptronSecond Language ProcessingSemantic FeaturesSemantic LabelingSemantic Role AnnotationUsage-based Language LearningWord Representation Learning
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.
18
SRILM - an extensible language modeling toolkit
Andreas Stolcke · 2002 · 4.4K citations
Discriminative training methods for hidden Markov models
Michael Collins · 2002 · 1.9K citations · Full text
Using predicate-argument structures for information extraction
Mihai Surdeanu, Sanda M. Harabagiu, John Williams et al. · 2003 · 370 citations · Full text