| Diego Molla and Michael Hess, `Dealing with ambiguities in an answer extraction system', in Workshop on Representation and Treatment of Syntactic Ambiguity in Natural Language Processing, pp. 21--24, Paris, (2000). ATALA. |
....decision in the dependency structure. After the disambiguator is run the first two fields are compared. Equal fields indicate a correct attachment decision in the dependency structure. Only the set of dependency structures that has the highest ratio of correct attachments passes the filter (Moll D. Hess M. 2000). ExtrAns includes besides transitive verbs all categories of verbs, multiple PP attachments, gerund and infinitive constructions. First the training was done with the Treebank corpus (Marcus M. et al 1993) the accuracy is reported to be 81.8 ) but it turned out that this corpus was not ....
MOLL, Diego ; HESS, Michael (2000) : "Dealing with ambiguities in an answer extraction system", in Workshop on Representation and Treatment of Syntactic Ambiguity in Natural Language Processing, pp. 21--24, Paris.
....reduces the complexity of parsing the AMM, by as much as 50 . Also, the output of LG has been extended to include the direction of the linkages as this information is vital for anaphora resolution and semantic analysis. As LG returns all possible parses, it is necessary to disambiguate among them [13]. The two possibilities for the prepositional phrase attachment returned in figure 2, will be reduced to (b) by the disambiguator as this linkage correctly identifies the dependency relations. The link Wd connects the subject coax cable to the wall. The wall functions as a dummy word at the ....
Diego Molla and Michael Hess, `Dealing with ambiguities in an answer extraction system', in Workshop on Representation and Treatment of Syntactic Ambiguity in Natural Language Processing, pp. 21--24, Paris, (2000). ATALA.
No context found.
Diego Moll and Michael Hess. 2000. Dealing with ambiguities in an answer extraction system. In Representation and Treatment of Syntactic Ambiguity in Natural Language Processing, Paris. ATALA.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC