|Abstract||A* PCFG parsing can dramatically reduce the time required to find the exact Viterbi parse by conservatively estimating outside Viterbi probabilities. We discuss various estimates and give efficient algorithms for computing them. On Penn treebank sentences, our most detailed estimate reduces the total number of edges processed to less than 3% of that required by exhaustive parsing, and even a simpler estimate which can be pre-computed in under a minute still reduces the work by a factor of 5. The algorithm extends the classic A* graph search procedure to a certain hypergraph associated with parsing. Unlike bestfirst and finite-beam methods for achieving this kind of speed-up, the A* parser is guaranteed to return the most likely parse, not just an approximation. The algorithm is also correct for a wide range of parser control strategies and maintains a worst-case cubic time bound.|
|Keywords||No keywords specified (fix it)|
No categories specified
(categorize this paper)
|Through your library||Only published papers are available at libraries|
Similar books and articles
Christopher Manning, An ¢¡¤£¦¥¨§ Agenda-Based Chart Parser for Arbitrary Probabilistic Context-Free Grammars.
Dan Klein & Christopher D. Manning, Parsing with Treebank Grammars: Empirical Bounds, Theoretical Models, and the Structure of the Penn Treebank.
Dan Klein & Christopher D. Manning, Fast Exact Inference with a Factored Model for Natural Language Parsing.
Added to index2009-01-28
Total downloads3 ( #213,250 of 722,774 )
Recent downloads (6 months)1 ( #60,541 of 722,774 )
How can I increase my downloads?