<?xml version="1.0" standalone="yes"?>
<Paper uid="P05-1076">
  <Title>Automatic Acquisition of Adjectival Subcategorization from Corpora</Title>
  <Section position="2" start_page="0" end_page="614" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> Research into automatic acquisition of lexical information from large repositories of unannotated text (such as the web, corpora of published text, etc.) is starting to produce large scale lexical resources which include frequency and usage information tuned to genres and sublanguages. Such resources are critical for natural language processing (NLP), both for enhancing the performance of [?]Part of this research was conducted while this author was at the University of Edinburgh Laboratory for Foundations of Computer Science.</Paragraph>
    <Paragraph position="1"> state-of-art statistical systems and for improving the portability of these systems between domains.</Paragraph>
    <Paragraph position="2"> One type of lexical information with particular importance for NLP is subcategorization. Access to an accurate and comprehensive subcategorization lexicon is vital for the development of successful parsing technology (e.g. (Carroll et al., 1998b), important for many NLP tasks (e.g. automatic verb classification (Schulte im Walde and Brew, 2002)) and useful for any application which can benefit from information about predicate-argument structure (e.g. Information Extraction (IE) (Surdeanu et al., 2003)).</Paragraph>
    <Paragraph position="3"> The first systems capable of automatically learning a small number of verbal subcategorization frames (SCFs) from English corpora emerged over a decade ago (Brent, 1991; Manning, 1993). Subsequent research has yielded systems for English (Carroll and Rooth, 1998; Briscoe and Carroll, 1997; Korhonen, 2002) capable of detecting comprehensive sets of SCFs with promising accuracy and demonstrated success in application tasks (e.g. (Carroll et al., 1998b; Korhonen et al., 2003)), besides systems for a number of other languages (e.g. (Kawahara and Kurohashi, 2002; Ferrer, 2004)).</Paragraph>
    <Paragraph position="4"> While there has been considerable research into acquisition of verb subcategorization, we are not aware of any systems built for adjectives. Although adjectives are syntactically less multivalent than verbs, and although verb subcategorization distribution data appears to offer the greatest potential boost in parser performance, accurate and comprehensive knowledge of the many adjective SCFs can improve the accuracy of parsing at several levels  (from tagging to syntactic and semantic analysis).</Paragraph>
    <Paragraph position="5"> Automatic SCF acquisition techniques are particularly important for adjectives because extant syntax dictionaries provide very limited coverage of adjective subcategorization.</Paragraph>
    <Paragraph position="6"> In this paper we propose a method for automatic acquisition of adjectival SCFs from English corpus data. Our method has been implemented using a decision-tree classifier which tests for the presence of grammatical relations (GRs) in the output of the RASP (Robust Accurate Statistical Parsing) system (Briscoe and Carroll, 2002). It uses a powerful task-specific pattern-matching language which enables the frames to be classified hierarchically in a way that mirrors inheritance-based lexica. As reported later, the system is capable of detecting 30 SCFs with an accuracy comparable to that of best state-of-art verbal SCF acquisition systems (e.g. (Korhonen, 2002)).</Paragraph>
    <Paragraph position="7"> Additionally, we present a novel tool for linguistic annotation of SCFs in corpus data aimed at alleviating the process of obtaining training and test data for subcategorization acquisition. The tool incorporates an intuitive interface with the ability to significantly reduce the number of frames presented to the user for each sentence.</Paragraph>
    <Paragraph position="8"> We discuss adjectival subcategorization in section 2 and introduce the system for SCF acquisition in section 3. Details of the annotation tool and the experimental evaluation are supplied in section 4.</Paragraph>
    <Paragraph position="9"> Section 5 provides discussion on our results and future work, and section 6 summarises the paper.</Paragraph>
  </Section>
class="xml-element"></Paper>