Đang chuẩn bị nút TẢI XUỐNG, xin hãy chờ
Tải xuống
Optimising for one grammatical representation, but evaluating over a different one is a particular challenge for parsers and n-best CCG parsing. We find that this mismatch causes many n-best CCG parses to be semantically equivalent, and describe a hashing technique that eliminates this problem, improving oracle n-best F-score by 0.7% and reranking accuracy by 0.4%. | Dependency Hashing for n-best CCG Parsing Dominick Ng and James R. Curran o-lab School of Information Technologies University of Sydney NSW 2006 Australia dominick.ng james.r.curran @sydney.edu.au Abstract Optimising for one grammatical representation but evaluating over a different one is a particular challenge for parsers and n-best CCG parsing. We find that this mismatch causes many n-best CCG parses to be semantically equivalent and describe a hashing technique that eliminates this problem improving oracle n-best F-score by 0.7 and reranking accuracy by 0.4 . We also present a comprehensive analysis of errors made by the C C CCG parser providing the first breakdown of the impact of implementation decisions such as supertagging on parsing accuracy. 1 Introduction Reranking techniques are commonly used for improving the accuracy of parsing Charniak and Johnson 2005 . Efficient decoding of a parse forest is infeasible without dynamic programming but this restricts features to local tree contexts. Reranking operates over a list of n-best parses according to the original model allowing poor local parse decisions to be identified using arbitrary rich parse features. The performance of reranking depends on the quality of the underlying n-best parses. Huang and Chiang 2005 s n-best algorithms are used in a wide variety of parsers including an n-best version of the C C CCG parser Clark and Curran 2007 Brennan 2008 . The oracle F-score of this parser calculated by selecting the most optimal parse in the n-best list is 92.60 with n 50 over a baseline 1-best F-score of 86.84 . In contrast the Charniak parser records an oracle F-score of 96.80 in 50-best mode 497 over a baseline of 91.00 Charniak and Johnson 2005 . The 4.2 oracle score difference suggests that further optimisations may be possible for CCG. We describe how n-best parsing algorithms that operate over derivations do not account for absorption ambiguities in parsing causing semantically identical parses to .
