In recent years, research in natural language processing has increasingly focused on normalizing SMS messages. Different well-defined approaches have been proposed, but the proble...
Richard Beaufort, Sophie Roekhaut, Louise-Am&eacut...
We reveal a previously unnoticed connection between dependency parsing and statistical machine translation (SMT), by formulating the dependency parsing task as a problem of word a...
Minimum Error Rate Training is the algorithm for log-linear model parameter training most used in state-of-the-art Statistical Machine Translation systems. In its original formula...
16:30 Generating and Validating Abstracts of Meeting Conversations: a User Study. Gabriel Murray, Giuseppe Carenini and Raymond Ng 16:30 - 16:45 Break Session 3: Sentence Level Gen...
In this paper we investigate the automatic generation and evaluation of sentential paraphrases. We describe a method for generating sentential paraphrases by using a large aligned...