<?xml version="1.0" standalone="yes"?>
<Paper uid="W06-2002">
  <Title>A Framework for Incorporating Alignment Information in Parsing</Title>
  <Section position="5" start_page="24" end_page="24" type="metho">
    <SectionTitle>
5 Discussion
</SectionTitle>
    <Paragraph position="0"> Oneoftheprimaryconcernsaboutthisframework is speed, since the decoding algorithm for our probabilisticmodelisnotpolynomial-timelikethe decodingalgorithmsforPCFGparsing. Nevertheless, in our experiments with shallow parsed 20word sentences, time was not a factor. Furthermore,inourongoing research applying thisprobabilistic framework tothe task ofPenn Treebank-style parsing, this approach appears to also be viableforthe40-wordsentences ofSections22and 23oftheWSJtreebank. Astrongmitigatingfactor of the theoretical intractibility is the fact that we have an anytime decoding algorithm, hence even  incaseswhenwecannotrunthealgorithmtocompletion(foraguaranteed optimalsolution), thealgorithm always returns somesolution, the quality of which increases over time. Hence we can tell the algorithm how much time it has to compute, and it will return the best solution it can compute inthattimeframe.</Paragraph>
    <Paragraph position="1">  Thisworksuggeststhatonecangetagoodqualityparserforanewparsingdomainwithrelatively null little effort (the features we chose are extremely simple and certainly could be improved on). The cross-lingual information that we used (namely, theforeignpreterminaltagsofthewordstowhich  ourspanwasalignedbyGIZA)didnotgiveasignificant improvement to our parser. However the  goalofthisworkwasnottomakedefinitivestatements about the value of crosslingual features in parsing, but rather to show a framework in which such crosslingual information could be easily incorporatedandexploited. Webelievewehaveprovidedthebeginningsofoneinthiswork,andwork null continues on finding more complex features that will improve performance well beyond the baseline. null</Paragraph>
  </Section>
  <Section position="6" start_page="24" end_page="24" type="metho">
    <SectionTitle>
Acknowledgement
</SectionTitle>
    <Paragraph position="0"> Theworkreported inthispaperwassupported by the Deutsche Forschungsgemeinschaft (DFG;German Research Foundation) in the Emmy Noether project PTOLEMAIOS on grammar learning from parallelcorpora.</Paragraph>
  </Section>
class="xml-element"></Paper>