cient Parsing for Information Extraction

Several (and successfull) Information Extraction systems have recently replaced the core parsing components with shallow but more ecient recognizers. In this paper we argue that the absence of an underlying grammatical recog-nizer, given the complex nature of several (non-english) languages , is a strong limitation for text processing functionali-ties, like those an IE system needs. We propose a robust and ecient syntactic recognizer mainly aimed to capture grammatical information crucial for several linguistic and non linguistic inferences. The proposed system is based on a novel architecture exploiting two major principles: lexicalization and stratication of the parsing process. As several linguistic theories (e.g. HPSG) and parsing frameworks (e.g. LTAG, SLTAG, lexicalized probabilistic parsing) suggest, lexicon-driven systems ensure the suitable forms of grammatical control for many complex phenomena. In our system an analysis guided by information on typical verb projections (e.g. verb subcat-egorization structures) is coupled with extended locality constraints (i.e. recognition of clause boundaries). Furthermore, stratication is also employed. A cascade of processing steps starts from chunk recognition and proceeds through clause analysis to dependency detection. Recognition of chunks allows to minimize the input ambiguity to the remaining phases. The resulting system is thus robust against ungrammatical phenomena (e.g. complex clause embedding, misspellings, unknown words). Eciency is also retained, although ambiguous phenomena (multiple PP attachments) are recognized. 1 Introduction Several (and successful) IE systems have recently replaced the core parsing components with shallow but more ecient recognizers [1, 8]. However, the absence of a grammatical rec-ognizer, given the complex nature of several (non-english) languages , is a strong limitation for text processing functionali-ties, like those an IE system needs. Let us provide a sentence, extracted and translated from a nancial corpus in Italian: 1 Assuming to have at disposal a certain budget level for an environmental recovery action, ACE s.p.a. intends to prepare the necessary plan to coordinate the following work activities, which will end in the completion of the operational implementation project. that exhibits a complex but very common structure in Ital-ian texts. Typical information to be extracted from the above sentence is the named organization (i.e., Ace), the type of intended activity (i.e., environmental recovery) and a variety of 1 see the Appendix for the Italian version. specications and participants to the core event. For example, understanding of the intended action of the Ace implies the recognition of the causative/agent role of the Ace itself in the subordinate clause. …