Abstract | We propose an improved, bottom-up method for converting CCG derivations into PTB-style phrase structure trees. |
Background | Our focus is on CCG to PTB conversion (Clark and Curran, 2009). |
Background | 2.1 Combinatory Categorial Grammar ( CCG ) |
Background | The lower half of Figure 1 shows a CCG derivation (Steedman, 2000) in which each word is assigned a category, and combinatory rules are applied to adjacent categories until only one remains. |
Introduction | Converting the Penn Treebank (PTB, Marcus et al., 1993) to other formalisms, such as HPSG (Miyao et al., 2004), LFG (Cahill et al., 2008), LTAG (Xia, 1999), and CCG (Hockenmaier, 2003), is a complex process that renders linguistic phenomena in formalism-specific ways. |
Introduction | Clark and Curran (2009) developed a CCG to PTB conversion that treats the CCG derivation as a phrase structure tree and applies handcrafted rules to every pair of categories that combine in the derivation. |
Introduction | Because their approach does not exploit the gener-alisations inherent in the CCG formalism, they must resort to ad-hoc rules over nonlocal features of the CCG constituents being combined (when a fixed pair of CCG categories correspond to multiple PTB structures). |
Abstract | Besides using traditional dependency parsers, we also use the dependency structures transformed from PCFG trees and predicate-argument structures (PASS) which are generated by an HPSG parser and a CCG parser. |
Experiments | In terms of root word comparison, we observe that MST and CCG share 87.3% of identical root words, caused by borrowing roots from MST to CCG . |
Experiments | Malt Berkeley PAS PAS CCG +syn +sem MST 70.5 62.5 69.2 53.3 87.3 (77.3) (64.6) (58.5) (5 8. |
Experiments | For example, CCG is worse than Malt in terms of P/R yet with a higher BLEU score. |
Gaining Dependency Structures | 2.5 CCG parsing |
Gaining Dependency Structures | We also use the predicate-argument dependencies generated by the CCG parser developed by Clark and Curran (2007). |
Gaining Dependency Structures | The algorithm for generating word-level dependency tree is easier than processing the PASS included in the HPSG trees, since the word level predicate-argument relations have already been included in the output of CCG parser. |
Introduction | A semantic dependency representation of a whole sentence, predicate-argument structures (PASS), are also included in the output trees of (1) a state-of-the-art head-driven phrase structure grammar (HPSG) (Pollard and Sag, 1994; Sag et al., 2003) parser, Enju1 (Miyao and Tsujii, 2008) and (2) a state-of-the-art CCG parser2 (Clark and Curran, 2007). |