Three New Probabilistic Models for Dependency Parsing: An Exploration

Details Three New Probabilistic Models for Dependency Parsing: An Exploration Three New Probabilistic Models for Dependency Parsing: An Exploration

1997-06-06

arxiv.org/abs/cmp-lg/9706003v2

Proceedings of the 16th International Conference on Computational Linguistics (COLING-96), Copenhagen, August 1996, pp. 340-34

Computer Science

Computation and Language

6 pages, LaTeX 2.09 packaged with 4 .eps files, also uses colap.sty and acl.bst

Scientific paper

After presenting a novel O(n^3) parsing algorithm for dependency grammar, we develop three contrasting ways to stochasticize it. We propose (a) a lexical affinity model where words struggle to modify each other, (b) a sense tagging model where words fluctuate randomly in their selectional preferences, and (c) a generative model where the speaker fleshes out each word's syntactic and conceptual structure without regard to the implications for the hearer. We also give preliminary empirical results from evaluating the three models' parsing performance on annotated Wall Street Journal training text (derived from the Penn Treebank). In these results, the generative (i.e., top-down) model performs significantly better than the others, and does about equally well at assigning part-of-speech tags.

Affiliated with

Also associated with

No associations

Rating

Three New Probabilistic Models for Dependency Parsing: An Exploration 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 Three New Probabilistic Models for Dependency Parsing: An Exploration, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Three New Probabilistic Models for Dependency Parsing: An Exploration will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-548224