Background: Biomedical literature, e.g., MEDLINE, contains a wealth of knowledge regarding functions of proteins. Major recurring biological concepts within such text corpora repr...
Multilingual parallel text corpora provide a powerful means for propagating linguistic knowledge across languages. We present a model which jointly learns linguistic structure for...
Most previous work on multilingual sentiment analysis has focused on methods to adapt sentiment resources from resource-rich languages to resource-poor languages. We present a nov...
Bin Lu, Chenhao Tan, Claire Cardie, Benjamin K. Ts...
Abstract. We present a new implication of Wu’s (1997) Inversion Transduction Grammar (ITG) Hypothesis, on the problem of retrieving truly parallel sentence translations from larg...
Corpus-based methods for natural language processing often use supervised training, requiring expensive manual annotation of training corpora. This paper investigates methods for ...