Abstract
Discriminative reranking is one method for constructing high-performance statistical parsers (Collins, 2000). A discriminative reranker requires a source of candidate parses for each sentence. This paper describes a simple yet novel method for constructing sets of 50-best parses based on a coarse-to-fine generative parser (Charniak, 2000). This method generates 50-best lists that are of substantially higher quality than previously obtainable. We used these parses as the input to a MaxEnt reranker (Johnson et al., 1999; Riezler et al., 2002) that selects the best parse from the set of parses for each sentence, obtaining an f-score of 91.0% on sentences of length 100 or less.
Original language | English |
---|---|
Title of host publication | Proceedings of the 43rd Annual Meeting of the Association for Computational Linguistics (ACL'2005) |
Place of Publication | Stroudsburg, PA |
Publisher | Association for Computational Linguistics (ACL) |
Pages | 173-180 |
Number of pages | 8 |
ISBN (Print) | 1932432515, 9781932432510 |
Publication status | Published - 2005 |
Externally published | Yes |
Event | 43rd Annual Meeting of the Association for Computational Linguistics, ACL-05 - Ann Arbor, MI, United States Duration: 25 Jun 2005 → 30 Jun 2005 |
Other
Other | 43rd Annual Meeting of the Association for Computational Linguistics, ACL-05 |
---|---|
Country/Territory | United States |
City | Ann Arbor, MI |
Period | 25/06/05 → 30/06/05 |