Seed sampling is critical in semi-supervised learning. This paper proposes a clusteringbased stratified seed sampling approach to semi-supervised learning. First, various clusteri...
In this paper, we investigate structured models for document-level sentiment classification. When predicting the sentiment of a subjective document (e.g., as positive or negative)...
Much NLP research on Multi-Word Expressions (MWEs) focuses on the discovery of new expressions, as opposed to the identification in texts of known expressions. However, MWE identi...
Tree Adjoining Grammars have well-known advantages, but are typically considered too difficult for practical systems. We demonstrate that, when done right, adjoining improves tran...
Within the communication process of human beings, the speaker's facial expression and lip-shape movement contains extremely rich language information. The hearing impaired, a...