Large-Scale Induction and Evaluation of Lexical Resources from the Penn-II Treebank

Large-Scale Induction and Evaluation of Lexical Resources from the Penn-II Treebank Ruth O’Donovan, Michael Burke, Aoife Cahill, Josef van Genabith, Andy Way National Centre for Language Technology and School of Computing Dublin City University Glasnevin Dublin 9 Ireland {rodonovan,mburke,acahill,josef,away}@computing.dcu.ie Abstract In this paper we present a methodology for ex- tracting subcategorisation frames based on an automatic LFG f-structure annotation algorithm for the Penn-II Treebank. We extract abstract syntactic function-based subcategorisation frames (LFG semantic forms), traditional CFG category- based subcategorisation frames as well as mixed function/category-based frames, with or without preposition information for obliques and particle in- formation for particle verbs. Our approach does not predefine frames, associates probabilities with frames conditional on the lemma, distinguishes be- tween active and passive frames, and fully reflects the effects of long-distance dependencies in the source data structures. We extract 3586 verb lem- mas, 14348 semantic form types (an average of 4 per lemma) with 577 frame types. We present a large-scale evaluation of the complete set of forms extracted against the full COMLEX resource. 1 Introduction Lexical resources are crucial in the construction of wide-coverage computational systems based on modern syntactic theories (e.g. LFG, HPSG, CCG, LTAG etc.). However, as manual construction of such lexical resources is time-consuming, error- prone, expensive and rarely ever complete, it is of- ten the case that limitations of NLP systems based on lexicalised approaches are due to bottlenecks in the lexicon component. Given this, research on automating lexical acqui- sition for lexically-based NLP systems is a partic- ularly important issue. In this paper we present an approach to automating subcategorisation frame ac- quisition for LFG (Kaplan and Bresnan, 1982) i.e. grammatical function-based systems. LFG has two levels of structural representation: structure, and f(unctional)-structure.c(onstituent)- LFG differ- entiates between governable (argument) and non- governable (adjunct) grammatical functions. Sub- categorisation requirements are enforced through semantic forms specifying the governable grammat- ical functions required by a particular predicate (e.g. FOCUS⟨(↑ SUBJ)(↑ OBLon)⟩). Our approach is based on earlier work on LFG semantic form extrac- tion (van Genabith et al., 1999) and recent progress in automatically annotating the Penn-II treebank with LFG f-structures (Cahill et al., 2004b). De- pending on the quality of the f-structures, reliable LFG semantic forms can then be generated quite simply by recursively reading off the subcategoris- able grammatical functions for each local pred value at each level of embedding in the f-structures. The work reported in (van Genabith et al., 1999) was small scale (100 trees), proof of concept and required considerable manual annotation work. In this paper we show how the extraction process can be scaled to the complete Wall Street Journal (WSJ) section of the Penn-II treebank, with about 1 mil- lion words in 50,000 sentences, based on the au- tomatic LFG f-structure annotation algorithm de- scribed in (Cahill et al., 2004b). In addition to ex- tracting grammatical function-based subcategorisa- tion frames, we also include the syntactic categories of the predicate and its subcategorised arguments, as well as additional details such as the prepositions required …

Content truncated to 500 words