tailieunhanh - Báo cáo khoa học: "Hybrid Parsing: Using Probabilistic Models as Predictors for a Symbolic Parser"

In this paper we investigate the benefit of stochastic predictor components for the parsing quality which can be obtained with a rule-based dependency grammar. By including a chunker, a supertagger, a PP attacher, and a fast probabilistic parser we were able to improve upon the baseline by , bringing the overall labelled accuracy to on the German NEGRA corpus. We attribute the successful integration to the ability of the underlying grammar model to combine uncertain evidence in a soft manner, thus avoiding the problem of error propagation. . | Hybrid Parsing Using Probabilistic Models as Predictors for a Symbolic Parser Kilian A. Foth Wolfgang Menzel Department of Informatics Universitat Hamburg Germany foth menzel @ Abstract In this paper we investigate the benefit of stochastic predictor components for the parsing quality which can be obtained with a rule-based dependency grammar. By including a chunker a supertagger a PP at-tacher and a fast probabilistic parser we were able to improve upon the baseline by bringing the overall labelled accuracy to on the German NEGRA corpus. We attribute the successful integration to the ability of the underlying grammar model to combine uncertain evidence in a soft manner thus avoiding the problem of error propagation. 1 Introduction There seems to be an upper limit for the level of quality that can be achieved by a parser if it is confined to information drawn from a single source. Stochastic parsers for English trained on the Penn Treebank have peaked their performance around 90 Charniak 2000 . Parsing of German seems to be even harder and parsers trained on the NEGRA corpus or an enriched version of it still perform considerably worse. On the other hand a great number of shallow components like taggers chunkers supertaggers as well as general or specialized attachment predictors have been developed that might provide additional information to further improve the quality of a parser s output as long as their contributions are in some sense com-plementory. Despite these prospects such possibilities have rarely been investigated so far. To estimate the degree to which the desired synergy between heterogeneous knowledge sources can be achieved we have established an experimental framework for syntactic analysis which allows us to plug in a wide variety of external predictor components and to integrate their contributions as additional evidence in the general decision-making on the optimal structural interpretation. We refer to this .