By Topic

Natural Language Processing and Knowledge Engineering, 2003. Proceedings. 2003 International Conference on

Date 26-29 Oct. 2003

Filter Results

Displaying Results 1 - 25 of 140
  • 2003 International Conference on Natural Language Processing and Knowledge Engineering (IEEE Cat. No.03EX703)

    Publication Year: 2003
    Request permission for commercial reuse | PDF file iconPDF (749 KB)
    Freely Available from IEEE
  • Precisiated natural language (PNL) - toward an enlargement of the role of natural languages in computation, deduction, definition and decision

    Publication Year: 2003, Page(s):3 - 4
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (83 KB) | HTML iconHTML

    It is a deep-seated tradition in science to view the use of natural languages in scientific theories as a manifestation of mathematical immaturity. In particular, a direct consequence is that existing scientific theories do not have the capability to operate on perception-based information. Such information is usually described in a natural language and is intrinsically imprecise, reflecting a fun... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Thesauruses for natural language processing

    Publication Year: 2003, Page(s):5 - 13
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (437 KB) | HTML iconHTML

    We argue that manual and automatic thesauruses are alternative resources for the same NLP tasks. This involves the radical step of interpreting manual thesauruses as classifications of words rather than word senses: the case for this is made. The range of roles for thesauruses within NLP is briefly presented and the WASPS thesaurus is introduced. Thesaurus evaluation is now becoming urgent. A rang... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Learning ontological knowledge from the Web

    Publication Year: 2003
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (30 KB) | HTML iconHTML

    Summary form only given. Two ongoing developments make the (semi-)automated construction of shallow semantic resources such as shallow ontologies increasingly feasible: advanced machine learning techniques and the growth of the Web. By decomposing the problem of knowledge acquisition for a shallow ontology into a series of steps, we apply the most appropriate resources and techniques to each step.... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Computer-aided generation of multiple-choice tests

    Publication Year: 2003
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (24 KB) | HTML iconHTML

    Summary form only given. The paper describes a novel automatic procedure for the generation of multiple-choice tests from electronic documents. In addition to employing various NLP techniques including term extraction and shallow parsing, the system makes use of language resources such as corpora and ontologies. The system operates in a fully automatic mode and also a semiautomatic environment whe... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Language resources in the semantic Web vision

    Publication Year: 2003, Page(s):16 - 18
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (157 KB) | HTML iconHTML

    Computational lexicons undoubtedly form an essential component to make the vision of the semantic Web a reality. In the semantic Web scenario, ontologies are the key components to manage knowledge, whereas, in human language technology (HLT), semantic description is committed to computational lexicons, which have to address the complexity of natural language. Semantic content processing lies at th... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • CI-based NLU methodology with applications in information content control

    Publication Year: 2003, Page(s):23 - 28
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (307 KB) | HTML iconHTML

    An attempt is made to propose a natural language understanding methodology based on comprehensive information (CI), the latter of which is an integrated concept of syntactic, semantic and pragmatic information. The major feature of the methodology is the full use of CI for sentence understanding in which the syntactic information is used for analyzing the sentence on whether it is grammatically le... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • N-best speech hypothesis reordering based on comprehensive information theory

    Publication Year: 2003, Page(s):29 - 32
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (226 KB) | HTML iconHTML

    This paper proposes a hypothesis reordering technique, based on a newly established theory, namely comprehensive information theory, to improve the accuracy of speech recognition in a man-machine dialog system. For each hypothesis, we calculate the amount of comprehensive information that hypothesis provided and then reorder N-best hypothesis according to the amount of comprehensive information. R... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Semantics-oriented language understanding with automatic adaptability

    Publication Year: 2003, Page(s):33 - 39
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (376 KB) | HTML iconHTML

    We propose a novel language understanding approach, the composition of classification, for utterances interpretation in a dialogue system. All the classification results including both the cascading information and the meaning information are composed to a nested semantic frame. This bypasses the traditional syntactic parsing and extracts semantics directly from plain text. To overcome the problem... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Pragmatic approach in natural language understanding

    Publication Year: 2003, Page(s):40 - 49
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (432 KB) | HTML iconHTML

    Natural languages that we use in daily conversation inevitably omit or insert various words. Incomplete sentences such as these are grammatically correct, but they prevent machine translation systems from correctly interpreting such sentences as they assume meanings only from sentence-to-sentence context. This is largely due to the fact that context is a social product defined by the participants ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Efficient implementation of morphological finite-state transition networks employing their statistical properties

    Publication Year: 2003, Page(s):50 - 55
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (352 KB) | HTML iconHTML

    Here we study numerically the structure of directed state transition graphs for several types of finite-state devices representing morphology of 16 languages. In all numerical experiments we have found that the distribution of incoming and outcoming links is highly skewed and is modelled well by the power law, not by the Poisson distribution typical for classical random graphs. Studied for three l... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A one-stage decoder for interpretation of natural speech

    Publication Year: 2003, Page(s):56 - 64
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (617 KB) | HTML iconHTML

    Current speech understanding systems are typically designed as multistage systems, although this theoretically gives rise to errors due to early decisions. We present a framework that offers the chance of reducing these errors by an integrated system which directly computes a semantic tree representation from the input speech signal through a token passing based one-stage decoder, called ODINS. In... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A framework for large scalable natural language call routing systems

    Publication Year: 2003, Page(s):65 - 71
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (438 KB) | HTML iconHTML

    A framework is proposed for enterprise automated call routing system development and large scalable natural language call routing application deployment based on IBM's speech recognition and NLU application engagement practices in recently years. To facilitate employing different call classification algorithms in an easy integration manner, this framework architecture provides a plug & play enviro... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Visual information assisted Mandarin large vocabulary continuous speech recognition

    Publication Year: 2003, Page(s):72 - 77
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (337 KB) | HTML iconHTML

    We present a general system framework of Mandarin audio-visual large vocabulary continuous speech recognition (LVCSR), which integrates visual information for better recognition performance and robustness. Several problems of audio-visual LVCSR are mainly addressed: lip tracking, visual feature extraction and audio-visual fusion. Firstly, the linear transform based lip tracking and low-level visua... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A syllable-based pseudo-articulatory approach to speech recognition

    Publication Year: 2003, Page(s):78 - 83
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (316 KB) | HTML iconHTML

    We present an account of the use of syllable structure as the basis for a novel approach to speech recognition. This contrasts with the serial organization of more conventional phonetic segments, and their use in speech recognition systems. It is demonstrated that working with syllables provides the basis for linguistically motivated speech recognition using pseudo-articulatory representations (PA... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Using linear smoothing to improve the modulation recognition performance

    Publication Year: 2003, Page(s):84 - 88
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (261 KB) | HTML iconHTML

    Automatic classification of modulation signals plays an important role in communication applications such as speech recognition, intelligent demodulator and electronic warfare etc. But how to improve the performance of the modulation classification algorithms in low SNR condition is an important problem during their practical application. We present a method that adopts linear smoothing to preproc... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A new knowledge representation based matter element system and the related extension reasoning

    Publication Year: 2003, Page(s):89 - 94
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (313 KB) | HTML iconHTML

    A matter element system extension AND/OR net is proposed, which has the representation ability of object-oriented knowledge representation, and the representation ability of creative thinking procedure as well. Moreover the matter element system extension AND/OR net can greatly increase data searching, data mining routes of object-oriented intelligent system. Meanwhile the rich reasoning based on ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Back to the future: a logical framework for temporal information representation and inferencing from financial news

    Publication Year: 2003, Page(s):95 - 101
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (431 KB) | HTML iconHTML

    Temporal information carries information about changes and time of the changes. Consider a company investing in another company. The former may choose to inject the money gradually with the amount and frequency depending on the performance of the latter. This shows that an event can be completed in multiple steps and at any given time before completion, it is partially completed. Thus, the status ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A method for knowledge representation with automatic uncertainty embodiment

    Publication Year: 2003, Page(s):102 - 107
    Cited by:  Papers (5)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (345 KB) | HTML iconHTML

    A key issue in dealing with knowledge representation is how to combine evidences from different sources, modelling adequately its uncertainty and conflict. A popular formalism to model someone's degrees of belief is the Theory of Evidence, or Dempster-Shafer Theory. This theory lacks a mean of automatic uncertainty embodiment, which limits the range of application of this theory, and, at the same ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Knowledge creation using class algebra

    Publication Year: 2003, Page(s):108 - 113
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (370 KB) | HTML iconHTML

    We present an overview of knowledge creation in a ternary Boolean algebra of classes and binary relations. The knowledge creation process involves both the induction and deduction processes to create the most "interesting" IS-A hierarchy of classes. This IS-A hierarchy will contain "interesting" class containments from which rules may be proposed and verified. These rules are proposed by looking a... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Knowledge representation and uncertainty management: applying Bayesian belief networks to a safety assessment expert system

    Publication Year: 2003, Page(s):114 - 119
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (449 KB) | HTML iconHTML

    We discuss knowledge representation and uncertainty management based on Bayesian belief networks (BBNs). Firstly, we carry out an investigation to the identified problems that occurs during applying safety standards. We conclude that most of these problems originate from the uncertainty nature in safety assessment. Then we provide an in-depth argument to explain why BBNs can deal with these proble... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Word sense disambiguation combining conceptual distance, frequency and gloss

    Publication Year: 2003, Page(s):120 - 125
    Cited by:  Papers (5)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (325 KB) | HTML iconHTML

    Word sense disambiguation (WSD) is the process of assigning a meaning to a word based on the context in which it occurs. The absence of sense tagged training data is a real problem for the word sense disambiguation task. We present a method for the resolution of lexical ambiguity which relies on the use of the wide-coverage noun taxonomy of WordNet and the notion of conceptual distance among conce... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Feature expansion for word sense disambiguation

    Publication Year: 2003, Page(s):126 - 131
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (339 KB) | HTML iconHTML

    One of the most serious obstacles in research on word sense disambiguation (WSD) is sparseness of training data. We describe and motivate a method of feature expansion as a means of resolving the data sparseness problem in supervised corpus-based WSD. The expanded features are extracted from an existing corpus and WordNet automatically. We use our method to supplement the feature expansion approac... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Multi-senses and multi-dependencies discovery among words

    Publication Year: 2003, Page(s):132 - 137
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (317 KB) | HTML iconHTML

    Word sense and word dependency benefit many applications. Manually constructed lexicon usually serves as a source for word sense and word dependency. However, there always requires very expensive work and extensive time consumption to compile it, simultaneously senses and relationships among words in these kinds of lexica are always missed. Automatically compiled lexica are under developing, the m... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Chinese word sense disambiguation by combining pseudo training data

    Publication Year: 2003, Page(s):138 - 143
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (378 KB) | HTML iconHTML

    In supervised methods of word sense disambiguation, sense tagged samples for training classifiers are needed. Since sense tagging for ambiguous words is expensive and labor intensive, it is worth looking for some reasonable substitutes. We suggest a kind of substitute for Chinese sense tagged data, which is called pseudo training data. The suggestion is based on a linguistic phenomenon in Chinese,... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.