UMIACS Computational Linguistics Colloquium

August 15, 2001,
1pm, AVW Room 2120

I will discuss the advantages of lexicalized tree-adjoining grammar as an alternative to lexicalized PCFG for statistical parsing, describing the induction of a probabilistic LTAG model from the Penn Treebank and evaluating its parsing performance. I will also talk about how this parser was modified for the Penn Chinese Treebank. Finally, I will speculate on -- and solicit suggestions for -- how these two parsers might be combined into a synchronous TAG-based system for translation between Chinese and English.

References

• Chiang, David. Statistical parsing with an automatically extracted tree adjoining grammar. Proc. ACL-2000, pages 456-463.

• Bikel, Daniel M. and David Chiang. Two statistical parsing models applied to the Chinese Treebank. Proc. Second Chinese Lang. Proc. Workshop, pages 1-6.

For the colloquium series schedule, see the UMD Computational Linguistics Colloquium Series web page at http://umiacs.umd.edu/~resnik/cl_colloquium/. If you are interested in meeting with the speaker, please contact Philip Resnik (resnik@umiacs.umd.edu).