Ever increasing size of the biomedical literature makes tapping into implicit knowledge in scientific literature a necessity for knowledge discovery. In this paper, a semantic par...
Pseudo-semantic labeling represents a novel approach for automatic content description of video. This information can be used in the context of a video database to improve browsin...
We present supervised approaches for detecting speaker roles and agreement/disagreement between speakers in broadcast conversation shows in three languages: English, Arabic, and M...
Standard algorithms for template-based information extraction (IE) require predefined template schemas, and often labeled data, to learn to extract their slot fillers (e.g., an ...
We describe a novel neural network architecture for the problem of semantic role labeling. Many current solutions are complicated, consist of several stages and handbuilt features...