Abstract | The definition of combinatory categorial grammar ( CCG ) in the literature varies quite a bit from author to author. |
Abstract | However, the differences between the definitions are important in terms of the language classes of each CCG . |
Abstract | We prove that a wide range of CCGs are strongly context-free, including the CCG of CCGbank and of the parser of Clark and Curran (2007). |
Introduction | Combinatory categorial grammar ( CCG ) is a variant of categorial grammar which has attracted interest for both theoretical and practical reasons. |
Introduction | On the practical side, we have corpora with CCG derivations for each sentence (Hockenmaier and Steedman, 2007), a wide-coverage parser trained on that corpus (Clark and Curran, 2007) and a system for converting CCG derivations into semantic representations (Bos et al., 2004). |
Introduction | However, despite being treated as a single unified grammar formalism, each of these authors use variations of CCG which differ primarily on which combinators are included in the grammar and the restrictions that are put on them. |
Background and motivation | Formalisms like HPSG (Pollard and Sag, 1994), LFG (Kaplan and Bresnan, 1982), and CCG (Steedman, 2000) are linguistically motivated in the sense that they attempt to explain and predict the limited variation found in the grammars of natural languages. |
Background and motivation | Combinatory Categorial Grammar ( CCG ; Steedman, 2000) is a lexicalised grammar, which means that all grammatical dependencies are specified in the lexical entries and that the production of derivations is governed by a small set of rules. |
Background and motivation | A CCG grammar consists of a small number of schematic rules, called combinators. |
Combining CCGbank corrections | When Hockenmaier and Steedman (2002) went to acquire a CCG treebank from the PTB, this posed a problem. |
Combining CCGbank corrections | There is no equivalent way to leave these structures underspecified in CCG , because derivations must be binary branching. |
Combining CCGbank corrections | This distinction is represented in the surface syntax in CCG , because the category of a verb must specify its argument structure. |
Introduction | We then describe a novel CCG analysis of NP predicate-argument structure, which we implement using NomBank (Meyers et al., 2004). |
Introduction | We then train and evaluate a parser for these changes, to investigate their impact on the accuracy of a state-of—the-art statistical CCG parser. |
Noun predicate-argument structure | 4.1 CCG analysis |
Parsing Evaluation | Some of the changes we have made correct problems that have caused the performance of a statistical CCG parser to be overestimated. |
Abstract | Combinatory Categorial Grammar ( CCG ) is generally construed as a fully lexicalized formalism, where all grammars use one and the same universal set of rules, and cross-linguistic variation is isolated in the lexicon. |
Abstract | In this paper, we show that the weak generative capacity of this ‘pure’ form of CCG is strictly smaller than that of CCG with gram-mar-specific rules, and of other mildly con-text-sensitive grammar formalisms, including Tree Adjoining Grammar (TAG). |
Abstract | Our result also carries over to a multi-modal extension of CCG . |
Introduction | Combinatory Categorial Grammar ( CCG ) (Steedman, 2001; Steedman and Baldridge, 2010) is an expressive grammar formalism with formal roots in combinatory logic (Curry et al., 1958) and links to the type-logical tradition of categorial grammar (Moortgat, 1997). |
Introduction | It is well-known that CCG can generate languages that are not context-free (which is necessary to capture natural languages), but can still be parsed in polynomial time. |
Introduction | Specifically, Vij ay-Shanker and Weir (1994) identified a version of CCG that is weakly equivalent to Tree Adjoining Grammar (TAG) (Joshi and Schabes, 1997) and other mildly context-sensitive grammar formalisms, and can generate non-context—free languages such as anbnc”. |
Abstract | We demonstrate the effectiveness of the method using a CCG supertagger and parser, obtaining significant speed increases on newspaper text with no loss in accuracy. |
Abstract | We also show that the method can be used to adapt the CCG parser to new domains, obtaining accuracy and speed improvements for Wikipedia and biomedical text. |
Adaptive Supertagging | CCG supertaggers are about 92% accurate when assigning a single lexical category to each word (Clark and Curran, 2004). |
Background | Figure 1 gives two sentences and their CCG derivations, showing how some of the syntactic ambiguity is transferred to the supertagging component in a lexicalised grammar. |
Background | Figure 1: Two CCG derivations with PP ambiguity. |
Background | Clark and Curran (2004) applied supertagging to CCG , using a flexible multi-tagging approach. |
Data | We have used Sections 02-21 of CCGbank (Hock-enmaier and Steedman, 2007), the CCG version of the Penn Treebank (Marcus et al., 1993), as training data for the newspaper domain. |
Data | For supertagger evaluation, one thousand sentences were manually annotated with CCG lexical categories and POS tags. |
Introduction | Parsing with lexicalised grammar formalisms, such as Lexicalised Tree Adjoining Grammar and Combinatory Categorial Grammar ( CCG ; Steed-man, 2000), can be made more efficient using a supertagger. |
Introduction | In this paper, we focus on the CCG parser and supertagger described in Clark and Curran (2007). |
Introduction | Since the CCG lexical category set used by the supertagger is much larger than the Penn Treebank POS tag set, the accuracy of supertagging is much lower than POS tagging; hence the CCG supertagger assigns multiple supertags1 to a word, when the local context does not provide enough information to decide on the correct supertag. |
Conclusion | Because the lexicon is the grammar in CCG , learning new word-category associations is grammar generalization and is of interest for grammar acquisition. |
Data | CCGbank was created by semiautomatically converting the Penn Treebank to CCG derivations (Hockenmaier and Steedman, 2007). |
Data | CCG-TUT was created by semiautomatically converting dependencies in the Italian Turin University Treebank to CCG derivations (Bos et al., 2009). |
Experiments | As such, these supertags are outside of the categorial system: their use in derivations requires phrase structure rules that are not derivable from the CCG combinatory rules. |
Experiments | EMG 1’s higher recall and precision indicate the tag transition distributions do capture general patterns of linkage between adjacent CCG categories, while EM ensures that the data filters out combinable, but unnecessary, bitags. |
Grammar informed initialization for supertagging | trast, supertags are detailed, structured labels; a universal set of grammatical rules defines how categories may combine with one another to project syntactic structure.2 Because of this, properties of the CCG formalism itself can be used to constrain learning—prior to considering any particular language, grammar or data set. |
Grammar informed initialization for supertagging | 2Note that supertags can be lexical categories of CCG (Steedman, 2000), elementary trees of Tree-adjoining Grammar (J oshi, 1988), or types in a feature hierarchy as in Head-driven Phrase Structure Grammar (Pollard and Sag, 1994). |
Introduction | A more challenging task is learning supertaggers for lexicalized grammar formalisms such as Combinatory Categorial Grammar ( CCG ) (Steedman, 2000). |
Introduction | Yet, this is an important task since creating grammars and resources for CCG parsers for new domains and languages is highly labor— and knowledge-intensive. |
Introduction | Baldridge (2008) uses grammar-informed initialization for HMM tag transitions based on the universal combinatory rules of the CCG formalism to obtain 56.1% accuracy on ambiguous word tokens, a large improvement over the 33.0% accuracy obtained with uniform initialization for tag transitions. |
A graph-based representation for LCFRS productions | If x1 and cc2 do not occur both in the same string yl or 3/2, then we say that there is a gap between cc1 and ccg . |
A graph-based representation for LCFRS productions | If cc1 <p cc2 and there is no gap between cc1 and ccg, then we write [cc1, ccg] to denote the set {cc1,cc2} U{cc|cc E V},, cc1 <}, c <}, ccg }. |
A graph-based representation for LCFRS productions | Note that the first condition means that 7“ and 7“’ are disjoint sets and, for any pair of vertices c E 7“ and cc’ E 7“’, either there is a gap between cc and cc’ or else there exists some ccg E V}, such that 9c <p ccg <p Jc’andflcg E’TUT’. |