Lexical Attraction Models (LAMs) were first introduced by Deniz Yuret in (Yuret 1998) to exemplify how an algorithm can learn word dependencies from raw text. His general thesis i...
The phenomenon of anticipatory coarticulation provides a basis for the observed asynchrony between the acoustic and visual onsets of phones in certain linguistic contexts. This ty...
Louis H. Terry, Karen Livescu, Janet B. Pierrehumb...
We argue that multilingual parallel data provides a valuable source of indirect supervision for induction of shallow semantic representations. Specifically, we consider unsupervi...
We present three systems for surface natural language generation that are trainable from annotated corpora. The first two systems, called NLG1 and NLG2, require a corpus marked on...
This paper describes the participation of the Technical University of Catalonia in the CLEF 2008 Question Answering on Speech Transcripts track. We have participated in the Englis...