Supertagging: Using Complex Lexical Descriptions in Natural Language Processing

Description

Investigations into employing statistical approaches with linguistically motivated representations and its impact on Natural Language processing tasks. The last decade has seen computational implementations of large hand-crafted natural language grammars in formal frameworks such as Tree-Adjoining Grammar (TAG), Combinatory Categorical Grammar (CCG), Head-driven Phrase Structure Grammar (HPSG), and Lexical Functional Grammar (LFG). Grammars in these frameworks typically associate linguistically motivated rich descriptions (Supertags) with words. With the availability of parse-annotated corpora, grammars in the TAG and CCG frameworks have also been automatically extracted while maintaining the linguistic relevance of the extracted Supertags. In these frameworks, Supertags are designed so that complex linguistic constraints are localized to operate within the domain of those descriptions. While this localization increases local ambiguity, the process of disambiguation (Supertagging) provides a unique way of combining linguistic and statistical information. This volume investigates the theme of employing statistical approaches with linguistically motivated representations and its impact on Natural Language Processing tasks. In particular, the contributors describe research in which words are associated with Supertags that are the primitives of different grammar formalisms including Lexicalized Tree-Adjoining Grammar (LTAG). Contributors Jens Bäcker, Srinivas Bangalore, Akshar Bharati, Pierre Boullier, Tomas By, John Chen, Stephen Clark, Berthold Crysmann, James R. Curran, Kilian Foth, Robert Frank, Karin Harbusch, Saša Hasan, Aravind Joshi, Vincenzo Lombardo, Takuya Matsuzaki, Alessandro Mazzei, Wolfgang Menzel, Yusuke Miyao, Richard Moot, Alexis Nasr, Günter Neumann, Martha Palmer, Owen Rambow, Rajeev Sangal, Anoop Sarkar, Giorgio Satta, Libin Shen, Patrick Sturt, Jun'ichi Tsujii, K. Vijay-Shanker, Wen Wang, Fei Xia Cover Title Page Contents Preface List of Figures Contributors 1 Introduction Part I: Creating and Organizing Supertags 2 From Treebanks to Tree-Adjoining Grammars 3 Developing Tree-Adjoining Grammars with Lexical Descriptions Part II: Supertagging and Parsing 4 Complexity of Parsing for Some Lexicalized Formalisms 5 Combining Supertagging and Lexicalized Tree-Adjoining Grammar Parsing 6 Discriminative Learning of Supertagging 7 A Nonstatistical Parsing-Based Approach to Supertagging 8 Nonlexical Chart Parsing for TAG Part III: Supertags in Related Formalisms 9 Supertagging for Efficient Wide-Coverage CCG Parsing 10 Constraint Dependency Grammars: SuperARVs, Language Modeling, and Parsing 11 Guiding a Constraint Dependency Parser with Supertags 12 Extraction of Type-Logical Supertags from the Spoken Dutch Corpus 13 Extracting Supertags from HPSG-Based Treebanks 14 Probabilistic Context-Free Grammars with Latent Annotations 15 Computational Paninian Grammar Framework Part IV: Linguistic and Psycholinguistic Issues 16 Lexicalized Syntax and Phonological Merge 17 Constraining the Form of Supertags with the Strong Connectivity Hypothesis Part V: Applications of Supertagging 18 Semantic Labeling and Parsing via Tree-Adjoining Grammars 19 Applications of HMM-Based Supertagging Author Index Subject Index