Federal agencies implement laws passed by the Congress by creating rules and regulations that can be applied in practice. During this process, staffs at the various agencies may r...
We explore morphology-based and sub-word language modeling approaches proposed for morphologically rich languages, and evaluate and contrast them for Turkish broadcast news transc...
We introduce an approach for physically-grounded natural language interpretation by robots which reacts appropriately to unanticipated physical changes in the environment and dyna...
Most previous work on trainable language generation has focused on two paradigms: (a) using a statistical model to rank a set of generated utterances, or (b) using statistics to i...
Many existing indexes on text work at the document granularity and are not effective in answering the class of queries where the desired answer is only a term or a phrase. In this...