Friday, 3 September 2010

Just a note on email summarization

Imagine that we have a set of mailing lists (e.g. Dbworld, Corpora-List, Linguist, BioNLP, moses-support, so on). Each of such a mailing list actually contains a bulk of questions and answers given by domain experts or semi-experts. A couple of situations can be raised:
Situation 1: a new user raises a question which had already been partially or fully answered through one or more email threads of mailing list. Need a question answering system or summarizer in this context???
Situation 2: a new user wants to search a topic of interest. A retrieval system needed???
Situation 3: such a mailing list needs a classification of email threads???
Situation 4: TBA

Any suggestions?


LingPipe - a toolkit for processing text using computational linguistics