Forest-based Search Algorithms in Parsing and Machine Translation

Posted in Conferences, Companies, Science on December 09, 2008

Many problems in Natural Language Processing (NLP) involves an efficient search for the best derivation over (exponentially) many candidates, especially in parsing and machine translation. In these cases, the concept of "packed forest" provides a compact representation of the huge search spaces, where efficient inference algorithms based on Dynamic Programming (DP) are possible.

In this talk we address two important open problems within this framework: exact k-best inference which is often used in NLP pipelines such as parse reranking and MT rescoring, and approximate inference when the search space is too big for exact search.

We first present a series of fast and exact k-best algorithms on forests, which are orders of magnitudes faster than previously used methods on state-of-the-art parsers such as Collins (1999). We then extend these algorithms for approximate search when the forests are too big for exact inference. We discuss two particular instances of this new method, forest rescoring for MT decoding with integrated language models, and forest reranking for discriminative parsing. In the former, our methods perform orders of magnitudes faster than conventional beam search on both state-of-the-art phrase-based and syntax-based systems, with the same level of search error or translation quality. In the latter, faster search also leads to better learning, where our approximate decoding makes whole-Treebank discriminative training practical and results in the best accuracy to date for parsers trained on the Treebank.

This talk includes joint work with David Chiang (USC Information Sciences Institute).

Liang Huang (2008). Forest Reranking: Discriminative Parsing with Non-Local Features.
Proceedings of ACL 2008 (to appear).

Liang Huang and David Chiang (2007). Forest Rescoring: Faster Decoding with Integrated Language Models.
Proceedings of ACL 2007.

Liang Huang and David Chiang (2005). Better k-best Parsing.
Proceedings of IWPT 2005.

Speaker: Liang Huang
Liang Huang is a final-year PhD student at the University of Pennsylvania, co-supervised by Aravind Joshi and Kevin Knight (USC/ ISI). He is mainly interested in the theoretical aspects of computational linguistics, in particular, efficient algorithms in parsing and machine translation, generic dynamic programming, and formal properties of synchronous grammars. He also works on applying computational linguistics to structural biology.

Google Tech Talks
March, 14 2008

Watch Video

Tags: Techtalks, Google, Conferences, Science, Computer Science, engEDU, Education, Google Tech Talks, Natural Language Processing, Companies