Catching the Drift: Probabilistic Content Models, with Applications to Generation and Summarization

Details Catching the Drift: Probabilistic Content Models, with Applications to Generation and Summarization Catching the Drift: Probabilistic Content Models, with Applications to Generation and Summarization

2004-05-12

arxiv.org/abs/cs/0405039v1

HLT-NAACL 2004: Proceedings of the Main Conference, pp. 113--120

Computer Science

Computation and Language

Best paper award

Scientific paper

We consider the problem of modeling the content structure of texts within a specific domain, in terms of the topics the texts address and the order in which these topics appear. We first present an effective knowledge-lean method for learning content models from un-annotated documents, utilizing a novel adaptation of algorithms for Hidden Markov Models. We then apply our method to two complementary tasks: information ordering and extractive summarization. Our experiments show that incorporating content models in these applications yields substantial improvement over previously-proposed methods.

Affiliated with

Also associated with

No associations

Rating

Catching the Drift: Probabilistic Content Models, with Applications to Generation and Summarization does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Catching the Drift: Probabilistic Content Models, with Applications to Generation and Summarization, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Catching the Drift: Probabilistic Content Models, with Applications to Generation and Summarization will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-536449