Constraint Based Integration of Deep and Shallow Parsing Techniques
نویسندگان
چکیده
To investigate the contributions of taggers or chunkers to the performance of a deep syntactic parser, Weighted Constraint Dependency Grammars have been extended to also take into consideration information from external sources. Using a weak information fusion scheme based on constraint optimization techniques, a parsing accuracy has been achieved which is comparable to other (stochastic) parsers.
منابع مشابه
Integrating deep and shallow natural language processing components: representations and hybrid architectures
We describe basic concepts and software architectures for the integration of shallow and deep (linguistics-based, semantics-oriented) natural language processing (NLP) components. The main goal of this novel, hybrid integration paradigm is improving robustness of deep processing. After an introduction to constraint-based natural language parsing, we give an overview of typical shallow processin...
متن کاملIntegrated Shallow and Deep Parsing: TopP Meets HPSG
We present a novel, data-driven method for integrated shallow and deep parsing. Mediated by an XML-based multi-layer annotation architecture, we interleave a robust, but accurate stochastic topological field parser of German with a constraintbased HPSG parser. Our annotation-based method for dovetailing shallow and deep phrasal constraints is highly flexible, allowing targeted and fine-grained ...
متن کاملConstraint-based RMRS Construction from Shallow Grammars
Semantic formalisms such as MRS [Copestake et al., 2003], UDRT [Reyle, 1993], or CLLS [Egg et al., 2001] provide elegant solutions for the treatment of semantic ambiguities in terms of underspecification. These semantic formalisms are not constrained to specific syntactic frameworks. MRS, for example, is mainly used with HPSG grammars, but may also be built from LFG grammars using co-descriptio...
متن کاملCompatible RMRS representations from RASP and the ERG
Various applications could potentially benefit from the integration of deep and shallow processing techniques. A universal representation, compatible between deep and shallow parsers, would enable such integration, allowing the advantages of both to be combined. This paper describes efforts to make RMRS such a representation. This work was done as part of DeepThought, funded under the 5th Frame...
متن کاملTopic Identification In Chinese Based On Centering Model
In this paper we are concerned with identifying the topics of sentences in Chinese texts. The key elements of the centering model of local discourse coherence are employed to identify the topic which is the most salient element in a Chinese sentence. Due to the phenomenon of zero anaphora occurring in Chinese texts frequently, in addition to the centering model, we further employ the constraint...
متن کامل