<?xml version="1.0" standalone="yes"?>
<Paper uid="W04-0305">
  <Title>Lookahead in Deterministic Left-Corner Parsing</Title>
  <Section position="8" start_page="80" end_page="80" type="concl">
    <SectionTitle>
8 Conclusions
</SectionTitle>
    <Paragraph position="0"> In this paper we have investigated issues in deterministic parsing by characterizing these issues in terms of the search procedure used by a statistical parser. We use a neural network to estimate the probabilities for an incremental history-based probability model based on left-corner parsing. Using an unconstrained search procedure to try to nd the most probable parse according to this probability model (i.e. non-deterministic parsing) results in state-of-the-art accuracy. Deterministic parsing is simulated by allowing the sequence of decisions between two words to be combined into a single parser action, and choosing the best single combined action based on the probability calculated using the basic left-corner probability model. All parses which do not use this chosen action are then pruned from the search. When this pruning is applied directly after each word, there is a large reduction in accuracy (8.3% F-measure) as compared to the non-deterministic search.</Paragraph>
    <Paragraph position="1"> Given the pervasive ambiguity in natural language, it is not surprising that this drastic pruning strategy results in a large reduction in accuracy. For this reason, deterministic parsers usually use some form of lookahead. Lookahead gives the parser more information about the sentence at the point when the choice of the next parser action takes place. We simulate the optimal use of k-word lookahead by summing over all partial parses which continue the given partial parse to the point where all k words in the lookahead have been generated.</Paragraph>
    <Paragraph position="2"> When expressed in terms of search, this means that the deterministic pruning is done k words behind a non-deterministic search for the best parse, based on a sum over the partial parses found by the non-deterministic search. When accuracy is plotted as a function of k ( gure 1), we found that there is a large increase in accuracy when the rst word of lookahead is added (only 2.7% F-measure below non-deterministic search). Further increases in the lookahead length have much less of an impact.</Paragraph>
    <Paragraph position="3"> We conclude that the rst word of lookahead is necessary for the success of any deterministic parser, but that additional lookahead is probably not necessary. The remaining error created by this model of deterministic parsing is probably best dealt with by investigating other aspect of the model of deterministic parsing assumed here, in particular the strict adherence to the left-corner parsing order.</Paragraph>
    <Paragraph position="4"> Despite the need to consider alternatives to the left-corner parsing order, these results do demonstrate that the left-corner parsing strategy proposed is surprisingly good at supporting deterministic parsing. This fact is important in making the non-deterministic search strategy used with this parser tractable. The observations made in this paper could lead to more sophisticated search strategies which further increase the speed of this or similar parsers without signi cant reductions in accuracy.</Paragraph>
  </Section>
class="xml-element"></Paper>