Robust Processing of Natural Language

  title={Robust Processing of Natural Language},
  author={Wolfgang Menzel},
  booktitle={Deutsche Jahrestagung f{\"u}r K{\"u}nstliche Intelligenz},
  • W. Menzel
  • Published in
    Deutsche Jahrestagung für K…
    13 July 1995
  • Computer Science
Previous approaches to robustness in natural language processing usually treat deviant input by relaxing grammatical constraints whenever a successful analysis cannot be provided by “normal” means. This schema implies, that error detection always comes prior to error handling, a behaviour which hardly can compete with its human model, where many erroneous situations are treated without even noticing them. The paper analyses the necessary preconditions for achieving a higher degree of robustness… 

Hybrid methods of natural language analysis

  • K. Foth
  • Computer Science
    Ausgezeichnete Informatikdissertationen
  • 2006
The automatic retrieval of syntax structure has been a longstanding goal of computer science, but one that still does not seem attainable because this kind of grammar development requires enormous effort by experts qualified in a particular language.

Robust parsing with weighted constraints

An architecture for robust parsing of natural language utterances has been developed, using a plausibility-based arbitration procedure to derive fairly rich structural representations, comprising aspects of syntax, semantics and other description levels of language.

Robustness beyond shallowness: incremental deep parsing

This work argues that with a systematic incremental methodology one can go beyond shallow parsing to deeper language analysis, while preserving robustness, and describes a generic system based on such a methodology and designed for building robust analyzers that tackle deeper linguistic phenomena than those traditionally handled by the now widespread shallow parsers.

Automatic and unsupervised methods in natural language processing

A supervised evaluation scheme that uses an error-free treebank to determine the robustness of a parser when faced with noisy input such as spelling errors and an unsupervised evaluation procedure for parser robustness that can reliably establish the robustity of an NLP system without any need of manual work are implemented.

Robust Processing for Constraint-based Grammar Formalisms

This thesis addresses the issue of how Natural Language Processing systems using ‘constraint-based’ grammar formalisms can be made robust, i.e. able to deal with input which is in some way ill-formed or extragrammatical, and proposes an approach to robust unification.

Robust parsing techniques for semantic analysis of natural language queries

The goal of this experiment was to investigate the eoeectiveness of a robust semantic analysis of analyzed speech input in a pipelined architecture, where no control is possible over the morphosyntactic analysis which precedes the semantic analysis and query formation.

Resolving anaphoric references on deficient syntactic descriptions

Two approaches are presented which generalize the verification of coindexing constraints to deficient descriptions and a partly heuristic method is described, which has been implemented and a provable complete method is specified.

Glr*: a robust grammar-focused parser for spontaneously spoken language

A general framework for combining a collection of parse evaluation measures into an integrated heuristic for evaluating and ranking the parses produced by the GLR* parser, that was designed to be robust to two particular types of extra-grammaticality: noise in the input, and limited grammar coverage.

HERALD Hybrid Environment for Robust Analysis of Language Data

This project addresses the problem of performing structura l and semantic analysis of data where the syntactic and semantic models of the domain are inadequate, and robust methods must be employed to

Parsing engineering and empirical robustness

An empirical definition of robustness based on the notion of performance is proposed and a framework for controlling the parser robustness in the design phase is presented.



Chart Parsing of Robust Grammars

Robustness is a formal behaviour of natural langatage grammars to assign a best partial description to linguistic events wltose strong description is inconsistent or cannot be constructed. Events of

Schema Method: A Framework for Correcting Grammatically Ill-formed Input

The schema method is a framework for correcting grammatically ill-formed input that overcomes the problem of relaxation control, the major drawback of the previous syntactically-oriented methods, and is also more efficient.

A Unified Process Model of Syntactic and Semantic Error Recovery in Sentence Understanding

This paper explores some of the ideas via a prototype computational model of sentence processing called COMPERE, and proposes a set of psychological experiments for testing the theories.

Managing Multiple Knowledge Sources in Constraint-Based Parsing of Spoken Language

A system which is capable of utilizing a variety of knowledge sources to select the most appropriate parse for a spoken sentence, which includes syntax, semantics, and contextual information is described.

A Cognitive Model of Sentence Interpretation: the Construction Grammar approach

A new, psychologically-plausible model of human sentence interpretation, based on a new model of linguistic structure, Construction Grammar, is described, which accounts for a wide variety of psycholinguistic results on lexical access, idiom processing, parsing preferences, and studies of gap-filling and other valence ambiguities.

Strategies for Adding Control Information to Declarative Grammars

Strategies are proposed for combining different kinds of constraints in declarative grammars with a detachable layer of control information. The added control information is the basis for

Structural Disambiguation with Constraint Propagation

We present a new grammatical formalism called Constraint Dependency Grammar (CDG) in which every grammatical rule is given as a constraint on word-to-word modifications. CDG parsing is formalized as

Head-driven phrase structure grammar

This book presents the most complete exposition of the theory of head-driven phrase structure grammar, introduced in the authors' "Information-Based Syntax and Semantics," and demonstrates the applicability of the HPSG approach to a wide range of empirical problems.

Robust Parsing of Spoken Dialogue Using Contextual Knowledge and Recognition Probabilities

This paper describes the linguistic processor of a spoken dialogue system and shows how the information content rate of the results can be improved if the selection is based on an integrated quality score combining word recognition scores and context-dependent semantic predictions.

Functional parallelism in spoken word-recognition