Parsing Unrestricted German Text with Defeasible Constraints
نویسندگان
چکیده
We present a parser for German that achieves a competitive accuracy on unrestricted input while maintaining a coverage of 100%. By writing well-formedness rules as declarative, defeasible constraints that integrate different sources of linguistic knowledge, very high robustness is achieved against all sorts of extragrammatical constructions.
منابع مشابه
A broad-coverage parser for German based on defeasible constraints
We present a parser for German that achieves a competitive accuracy on unrestricted input while maintaining a coverage of 100%. By writing well-formedness rules as declarative, defeasible constraints that integrate different sources of linguistic knowledge, very high robustness is achieved against all sorts of language error.
متن کاملWriting Weighted Constraints for Large Dependency Grammars
Implementing dependency grammar as a set of defeasible declarative rules has fundamental advantages such as expressiveness, automatic disambiguation, and robustness. Although an implementation and a successful large-scale grammar of German are available, so far the construction of constraint dependency grammars has not been described at length. We report on techniques that were used to write th...
متن کاملRobust German Noun Chunking With a Probabilistic Context-Free Grammar
We present a noun chunker for German which is based on a head-lexicalised probabilistic contextfree grammar. A manually developed grammar was semi-automatically extended with robustness rules in order to allow parsing of unrestricted text. The model parameters were learned from unlabelled training data by a probabilistic context-free parser. For extracting noun chunks, the parser generates all ...
متن کاملThe Lexicon-Grammar Balance in Robust Parsing of Italian
What is the role of lexical information in robust parsing of unrestricted texts? In this paper we provide experimental evidence showing that, in order to strike the balance between robustness and coverage needed for practical NLP applications, judicious use of positive lexical evidence given a text should be complemented with a battery of dynamic parsing strategies aimed at solving local constr...
متن کاملAPOLN: A Partial Parser Of Unrestricted Text
In this paper, we present APOLN (Analizador Parcial de Oraciones en Lenguaje Natural): a partial parser of unrestricted natural language sentences based on finite-state techniques. Partial parsing has been used in several applications: syntactic parsing of unrestricted texts, data extraction systems, machine translation, solving the attachment ambiguity, speech recognition systems, text summari...
متن کامل