<?xml version="1.0" standalone="yes"?>
<Paper uid="C00-1010">
  <Title>An Empirical Evaluation of LFG-DOP</Title>
  <Section position="2" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> We present an empirical ewduation of the LFG-DOP model introduced by Bed &amp; Kaplan (1998). LFG-DOP is a Data-Oriented Parsing (DOP) model (Bed 1993, 98) based on the syntactic representations of Lexical-Functional Grammar (Kaplan &amp; Bresnan 1982). A DOP model provides linguistic representations lot- an tmlimitcd set of sentences by generalizing from a given corptts of annotated exemphu's, it operates by decomposing the given representations into (arbitrarily large) fi'agments and recomposing those pieces to analyze new sentences.</Paragraph>
    <Paragraph position="1"> The occurrence-frequencies of the fragments are used to determine the most probable analysis of a sentence.</Paragraph>
    <Paragraph position="2"> So far, DOP models have been implelnented for phrase-structure trees and logical-semantic representations (cf. Bed 1993, 98; Sima'an 1995, 99; Bonnema el al. 1997; Goodman 1998). However, these DOP models are limited in that they cannot accotmt for underlying syntactic and semantic dependencies that are not reflected directly in a surface tree. DOP models for a number of richer representations have been explored (van den Berg et al. 1994; Tugwell 1995), but these approaches have remained context-free in their generative power. In contrast, Lexical-Functional Grammar (Kaplan &amp; Bresnan 1982) is known to be beyond context-free. In Bed &amp; Kaplan (1998), a first DOP model was proposed based on representations defined by LFG theory (&amp;quot;LFG-DOP&amp;quot;). I This model was I DOP models have recently also been proposed for Tree-Adjoining Grammar and Head-driven Phrase Structure Grammar (cf. Neumann &amp; Flickinger 1999).</Paragraph>
    <Paragraph position="3"> studied fi'om a mathematical perspective by Cormons (1999) who also accomplished a first simple experinacnt with LFG-DOP. Next, Way (1999) studied LFG-DOP as an architecture for machine translation. The current paper contains tile first extensive empMeal evaluation of LFG-DOP on the currently available LFG-annotatcd corpora: the Verbmobil corpus and the Itomecentre corpus. Both corpora were annotated at Xerox PARC.</Paragraph>
    <Paragraph position="4"> Out&amp;quot; parser uses fragments from LFG-annotated sentences to parse new sentences, and Monte Carlo lechniques to compute the most probable parse.</Paragraph>
    <Paragraph position="5"> Although our main goal is to lest Bed &amp; Kaplan's LFGl)OP model, we will also test a modified version o1' LFG-DOP which uses a different model for computing fragment probabilities. While Bed &amp; Kaplan treat all fragments probabilistically equal regardless whether they contain generalized features, we will propose a more fine-grained probability model which treats fragments with generalized features as previously unseen events and assigns probabilities to these fi'agments by means of discotmting. The experiments indicate that our probability model outperforms Bed &amp; Kaplan's probability model on the Verbmobil and Homecentre corpora.</Paragraph>
    <Paragraph position="6"> The rest of this paper is organized as follows: we first summarize the LFG-DOP model and go into our proposed extension. Next, we explain the Monte Carlo parsing technique for estimating lhe most probable LFGparse o1' a sentence. In section 3, we test our parser on sentences from the LFG-annotated corpora.</Paragraph>
  </Section>
class="xml-element"></Paper>