By Topic

2005 International Conference on Natural Language Processing and Knowledge Engineering

Oct. 30 2005-Nov. 1 2005

Filter Results

Displaying Results 1 - 25 of 171
  • Proceedings of the 2005 12th IEEE International Conference on Natural Language Processing and Knowledge Engineering (IEEE NLP-KE '05) (IEEE Cat. No. 05EX1156)

    Publication Year: 2005
    Request permission for commercial reuse | PDF file iconPDF (1212 KB)
    Freely Available from IEEE
  • [Title page]

    Publication Year: 2005, Page(s): 1
    Request permission for commercial reuse | PDF file iconPDF (355 KB)
    Freely Available from IEEE
  • Copyright page

    Publication Year: 2005, Page(s): 1
    Request permission for commercial reuse | PDF file iconPDF (55 KB)
    Freely Available from IEEE
  • Program message

    Publication Year: 2005, Page(s): 1
    Request permission for commercial reuse | PDF file iconPDF (250 KB) | HTML iconHTML
    Freely Available from IEEE
  • Program message

    Publication Year: 2005, Page(s): 1
    Request permission for commercial reuse | PDF file iconPDF (128 KB) | HTML iconHTML
    Freely Available from IEEE
  • Conference committee

    Publication Year: 2005, Page(s):1 - 4
    Request permission for commercial reuse | PDF file iconPDF (220 KB)
    Freely Available from IEEE
  • Schedule/agenda

    Publication Year: 2005, Page(s):1 - 2
    Request permission for commercial reuse | PDF file iconPDF (269 KB)
    Freely Available from IEEE
  • Table of contents

    Publication Year: 2005, Page(s):1 - 10
    Request permission for commercial reuse | PDF file iconPDF (1202 KB)
    Freely Available from IEEE
  • Natural language processing and knowledge

    Publication Year: 2005
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (78 KB) | HTML iconHTML

    Summary form only given. Natural language processing (NLP) requires varieties of knowledge. When we consider about man-machine dialogue we have to prepare lots of knowledge, and also strong inference functions such as logical inference and common sense reasoning. In this paper the author explains some new developments in knowledge for computational linguistics, then discuss about what kind of know... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Moving toward semantics for language processing: recent advances in resource construction and application

    Publication Year: 2005
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (104 KB)

    Summary form only given. In this paper the author describes the recent work at various locations, focusing on the resource components required (including ISI's symbol definition ontology Omega and the BBN-UPenn-Colorado-ISI large corpus OntoBank of (shallow) meaning representations) and the resources and methods one needs to build them (including existing ontologies, human annotation procedures, a... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • To have linguistic tree structures in statistical machine translation?

    Publication Year: 2005, Page(s):3 - 6
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (904 KB) | HTML iconHTML

    Statistical approaches are dominating the MT field currently, as they fit the non-deterministic characteristic of NLP naturally making the system implementation more manageable by shifting the complexity control mechanism from human to the computer, and ensure global optimization (over training data) by jointly considering all the data during training stage. Compared to not-linguistically-motivate... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Shallow language processing, deep language processing and domain ontologies

    Publication Year: 2005, Page(s):7 - 8
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (328 KB) | HTML iconHTML

    A new line of our research concerns the combination of shallow processing, deep processing and domain ontologies for question answering. In our QA system QUETAL, we combine question answering on the basis of structured data with open domain IR supported question answering as it can be employed for questioning the Web. The new approach exploits RMRS as the formalism for translating natural language... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Application of Boosting to Chinese word sense disambiguation

    Publication Year: 2005, Page(s):9 - 13
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1040 KB) | HTML iconHTML

    AdaBoost.M1 is a well known boosting-based method for improving the accuracy of a given machine-learning algorithm. In this paper, we modify AdaBoost.M1 for Chinese word sense disambiguation. Unlike AdaBoost.M1 that adapts weights of training sets, in our modified algorithm, we provide a new method to adapt the classifiers' weights. The base classifiers are trained on a small set of labeled exampl... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Abbreviation disambiguation using semantic abstraction of symbols and numeric terms

    Publication Year: 2005, Page(s):14 - 19
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (2736 KB) | HTML iconHTML

    We propose an abbreviation disambiguation approach that utilizes semantic representation of symbols and numeric terms as well as the words in clinical documents. While majority of related works treats symbols and numeric words as stopword, we show that they play an important role especially in coarse-grained documents such as CDA (clinical document architecture) documents, which contain a lot of j... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Word sense disambiguation using multi-engine collaborative boostrapping

    Publication Year: 2005, Page(s):20 - 25
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (976 KB) | HTML iconHTML

    In this paper we proposed a new word sense disambiguation method, called multi-engine collaborative bootstrapping (MCB) that combines different types of corpora and also uses two languages to bootstrapping. MCB contains the bilingual bootstrapping as its kernel algorithm that leads to incremental knowledge acquisition. EM model is performed to train parameters in base learner. Feature translation ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Rules selection in word sense disambiguation using Adaboost

    Publication Year: 2005, Page(s):26 - 29
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1552 KB) | HTML iconHTML

    Boosting algorithm is confirmed as a promising and practical machine learning method which has successfully been applied to some classification problems. Word sense disambiguation system using Boosting acquired the state-of-the-art performance. This paper explores the primary but unavoidable problem of rules selection in Adaboost applied to word sense disambiguation system, presenting the relation... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Unsupervised word sense disambiguation and rules extraction using non-aligned bilingual corpus

    Publication Year: 2005, Page(s):30 - 35
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1808 KB) | HTML iconHTML

    This paper presents a statistical word sense disambiguation with application in Portuguese-Chinese machine translation systems. Due to the limited availability of Portuguese-Chinese resources in the form of digital corpora and annotated Treebank, an unsupervised learning and a non-aligned bilingual corpus are applied. The proposed method first identifies words related to each of the ambiguous word... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Clustering-based feature selection for verb sense disambiguation

    Publication Year: 2005, Page(s):36 - 41
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1408 KB) | HTML iconHTML

    This paper presents a novel feature selection algorithm for supervised verb sense disambiguation. The algorithm disambiguates and aggregates WordNet synsets of a verb's noun phrase (NP) arguments in the training data. It was then used to filter out irrelevant WordNet semantic features introduced by the ambiguity of verb NP arguments. Experimental results showed that our new feature selection metho... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Manchu handwritten character recognition post processing based on the combination language model

    Publication Year: 2005, Page(s):42 - 46
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (904 KB) | HTML iconHTML

    This paper presents a combination Manchu language model on post-processing optimization for handwritten Manchu characters recognition. The thinking of this model is take corpus as post-processing core and rule assistant correction. The model is based on a Manchu machine dictionary. The aim of work is to explore the language model in order to optimize the recognition accuracy rate. Present method f... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Mining data from simulation of beer production

    Publication Year: 2005, Page(s):47 - 51
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (2632 KB) | HTML iconHTML

    Data mining is a methodology for the extraction of knowledge from data, especially, knowledge relating to a problem that we want to solve. Data mining from simulation outputs is performed in this paper, it focuses on techniques for extracting knowledge from simulation outputs for beer production and optimizing devices and labors with certain target. We first set up one simulation model for beer pr... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Improving collocation extraction by using syntactic patterns

    Publication Year: 2005, Page(s):52 - 57
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1224 KB) | HTML iconHTML

    A study on using syntactic patterns to improve window-based collocation extraction systems is presented. The support collocation patterns and reject collocation patterns retrieved from a chunked corpus and are used in two different strategies. The first strategy uses only the support patterns in preprocessing stage whereas the second strategy incorporates both the support and the reject patterns i... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The statistic properties of Chinese semantic network in HowNet

    Publication Year: 2005, Page(s):58 - 61
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1520 KB) | HTML iconHTML

    We extract a network from HowNet, a semantic network based on relations of concept explanations, and calculate its statistic properties. We found it is a complex network with features of small-world and scale-free. Structure of semantic networks based on neighboring words in sentence, conceptual similarity and association also have features of small-world and scale-free. Most exponents of power la... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Research on nominal compounding in Chinese

    Publication Year: 2005, Page(s):62 - 67
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1992 KB) | HTML iconHTML

    This paper provides a solution to analyze semantic relations of Chinese nominal phrases. Firstly, it gives an introduction about the basic contents of the Connet (Conceptual Network) that is a kind of knowledge representation architecture. Then, this paper proposes a semantic compounding model that is being used for semantic representation and semantic analysis in our research. Particularly, the M... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Automatically acquiring part of speech correcting rules of multi-category words based on incomplete decision tables

    Publication Year: 2005, Page(s):68 - 72
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1056 KB) | HTML iconHTML

    Part of speech (POS) tagging is a basic subject for Chinese information processing. In general, the existence of multi-category words greatly affects the processing quality of corpora. High efficient methods and automatically correcting techniques for multi-category word tagging are the keys for improving tagging precision. In this paper, for part of speech correcting of multi-category word, a mod... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A parsing algorithm of natural language based on operator precedence

    Publication Year: 2005, Page(s):73 - 78
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1288 KB) | HTML iconHTML

    To deal with the problems in the current parsing method of natural language, a language model based on purely typed binary relations is proposed in this paper, which is quite different from classical context-free grammar, Chomsky normal form and dependency grammar. The completeness of language structure coverage is easily captured using the proposed language model, so long as the binary relations ... View full abstract»

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