Trainable Methods for Surface Natural Language Generation

Details Trainable Methods for Surface Natural Language Generation Trainable Methods for Surface Natural Language Generation

2000-06-13

arxiv.org/abs/cs/0006028v1

Proceedings of the 1st Meeting of the North American Chapter of the Association for Computational Linguistics (NAACL 2000). Pa

Computer Science

Computation and Language

LaTeX, 8 pages

Scientific paper

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 only with domain-specific semantic attributes, while the last system, called NLG3, requires a corpus marked with both semantic attributes and syntactic dependency information. All systems attempt to produce a grammatical natural language phrase from a domain-specific semantic representation. NLG1 serves a baseline system and uses phrase frequencies to generate a whole phrase in one step, while NLG2 and NLG3 use maximum entropy probability models to individually generate each word in the phrase. The systems NLG2 and NLG3 learn to determine both the word choice and the word order of the phrase. We present experiments in which we generate phrases to describe flights in the air travel domain.

Affiliated with

Also associated with

No associations

Rating

Trainable Methods for Surface Natural Language Generation 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 Trainable Methods for Surface Natural Language Generation, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Trainable Methods for Surface Natural Language Generation will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-710594