<?xml version="1.0" standalone="yes"?>
<Paper uid="N06-1056">
  <Title>Learning for Semantic Parsing with Statistical Machine Translation</Title>
  <Section position="8" start_page="444" end_page="445" type="concl">
    <SectionTitle>
7 Conclusion
</SectionTitle>
    <Paragraph position="0"> We have presented a novel statistical approach to semantic parsing in which a word-based alignment model is used for lexical learning, and the parsing model itself can be seen as a syntax-based translation model. Our method is like many phrase-based translation models, which require a simpler, word-based alignment model for the acquisition of a phrasal lexicon (Och and Ney, 2003). It is also similar to the hierarchical phrase-based model of Chiang (2005), in which hierarchical phrase pairs, essentially SCFG rules, are learned through the use of a simpler, phrase-based alignment model. Our work shows that ideas from compiler theory (SCFG) and machinetranslation(wordalignment models)can be successfully applied to semantic parsing, a closely-related task whose goal is to translate a natural language into a formal language.</Paragraph>
    <Paragraph position="1"> Lexicallearningrequireswordalignmentsthatare phrasally coherent. We presented a simple greedy  algorithmforremovinglinksthatdestroyphrasalcoherence. Althoughitisshowntobequiteeffectivein the current domains, it is preferable to have a more principled way of promoting phrasal coherence. The problem is that, by treating MRL productions as atomic units, current word-based alignment models have no knowledge about the tree structure hidden in a linearized MR parse. In the future, we would like to develop a word-based alignment model that  is aware of the MRL syntax, so that better lexicons can be learned.</Paragraph>
  </Section>
class="xml-element"></Paper>