By Topic

2007 International Conference on Natural Language Processing and Knowledge Engineering

Aug. 30 2007-Sept. 1 2007

Filter Results

Displaying Results 1 - 25 of 91
  • [Front cover]

    Publication Year: 2007, Page(s): 1
    Request permission for commercial reuse | PDF file iconPDF (305 KB)
    Freely Available from IEEE
  • [Breaker page]

    Publication Year: 2007, Page(s): 1
    Request permission for commercial reuse | PDF file iconPDF (29 KB)
    Freely Available from IEEE
  • [Advertisements]

    Publication Year: 2007, Page(s):I - XII
    Request permission for commercial reuse | PDF file iconPDF (969 KB)
    Freely Available from IEEE
  • Table of contents

    Publication Year: 2007, Page(s):VI - XI
    Request permission for commercial reuse | PDF file iconPDF (4382 KB)
    Freely Available from IEEE
  • Conceptual difference between WordNet and HowNet

    Publication Year: 2007, Page(s): 1
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (299 KB)

    By comparison between WordNet and HowNet in their fundamentals, the paper discusses some essential theoretical issues on the construction of knowledge resources for NLP. It is focused on: (1) Human-orientation vs. computer-orientation; (2) Human-annotation vs. machine-computation; (3) Word-based vs. concept-based; (4) Synsets vs. sememes; (5) Definition in natural language vs. representation in st... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Towards Shallow Semantics: The OntoNotes Project

    Publication Year: 2007, Page(s):2 - 3
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1316 KB)

    Summary form only given. Many natural language processing (NLP) applications could benefit from a richer model of text meaning than the bag-of-words and n-gram models that currently predominate. Despite theoretical interest since the 1960s, however, no large-scale model exists; in fact, it is not even clear what such a model should minimally include. However, the introduction of large-scale public... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • How to link information in text with knowledge ------ Case study of text mining for pathway construction

    Publication Year: 2007, Page(s): 4
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (770 KB) | HTML iconHTML

    In this paper, we present a new direction of research which deploys these TM technologies to construct and maintain data bases organized in the form of pathway, by associating parts of papers with relevant portions of a pathway and vice versa. In order to materialize this scenario, we have being constructing a corpus (GENIA Pathway annotation) which associates portions of papers with specific part... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The Generation of Referring Expressions: Where We've Been, How We Got Here, and Where We're Going

    Publication Year: 2007, Page(s): 5
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (462 KB)

    Summary form only given. The task of referring expression generation is concerned with determining what semantic content should be used in a reference to an intended referent so that the hearer will be able to identify that referent. The task has been a focus of interest within natural language generation at least since the early 1980s, in part because the problem appears relatively well-defined. ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Methods and Applications for Relation Detection Potential and Limitations of Automatic Learning in IE

    Publication Year: 2007, Page(s):6 - 10
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (4495 KB) | HTML iconHTML

    The detection of relation instances is a central functionality for the extraction of structured information from unstructured textual data and for gradually turning texts into semi-structured information. Experience from many years of shared-task efforts in the MUC and ACE frameworks has led to promising initial results but also to frustrating barriers. But the systematic collective efforts have a... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Resource-based Natural Language Processing

    Publication Year: 2007, Page(s):11 - 12
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1291 KB) | HTML iconHTML

    Research on natural language processing (NLP) started with so-called rule-based methodology, however, compilation of huge amount of grammar rules and dictionary entries are too difficult to develop practical systems. Then, trend of NLP research shifted to corpus-based, or statistical systems. Thanks to the rapid improvement of computer power and data storage, nowadays we can utilize huge amount of... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Towards a new generation of Language Resources: global trends and international convergences

    Publication Year: 2007, Page(s): 13
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (803 KB) | HTML iconHTML

    Summary form only given. Language resources (LR) and semantics, dynamic resources automatically acquired, interoperability among LRs and Language Technology (LT), and how to go for a new generation of LRs in the Semantic Web (SW) framework, pointing at the potentialities and the need of a cross-fertilisation between the two communities of Human Language Technology (HLT) and SW. Large scale LRs are... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • IT Ontology and Semantic Technology

    Publication Year: 2007, Page(s):14 - 15
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1515 KB) | HTML iconHTML

    IT (information technology) ontology is to be used for analyzing the information technology as well as for enhancing it. Semantic technology is compared with the syntactic one. Ontology plays a backbone for meaning-centered reconfiguration of syntactic structure, which is one aspect of semantic technology. The purpose of use of IT ontology will be categorized into two things: to capture the right ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Logical Description of Metaphor Analysis

    Publication Year: 2007, Page(s):16 - 21
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (5626 KB) | HTML iconHTML

    This paper aims to use logical techniques to describe how metaphors are analyzed. Metaphor analysis process functions as one of the most important strategies to uncover implied information in discourse understanding. A metaphor analysis logic system is developed and presented in terms of its definitions, axiomatic system, inference rules, properties, semantic interpretations and applications. The ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Building New Field Association Word Candidates Automatically Using Search Engine

    Publication Year: 2007, Page(s):22 - 27
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (5745 KB) | HTML iconHTML

    With increasing popularity of the Internet and tremendous amount of on-line text, automatic document classification is important for organizing huge amounts of data. Readers can know the subject of many document fields by reading only some specific Field Association (FA) words. Document fields can be decided efficiently if there are many FA words and if the frequency rate is high. This paper propo... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Experiments of E-Mail Filtering Method Based on Sender, Sentence Type, Existence of Time Expression, and Subject of Mail Contents

    Publication Year: 2007, Page(s):28 - 35
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (8901 KB) | HTML iconHTML

    Filtering is a method of attaining only the wanted data and blocking the unwanted ones. Using this technology, the users can extract on the data that satisfy the query. As the previous studies use the single data, frequency of the data for example, it cannot be considered as the effective filtering method. What is needed is the effective technology that can process the electronic network documents... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Emotion Recognition from Text based on the Rough Set Theory and the Support Vector Machines

    Publication Year: 2007, Page(s):36 - 41
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (6242 KB) | HTML iconHTML

    In recent years, several methods on human emotion recognition have been published. But computer application on Chinese natural language processing (NLP) is still on the starting stage. In this paper, we proposed a scheme that emotion recognition from text through classification with the rough set theory and the support vector machines (SVMs). The basic steps are firstly to sample data sets, to bui... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Markov Logic Network Learning Algorithm From Relational Missing Data

    Publication Year: 2007, Page(s):42 - 49
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (7098 KB) | HTML iconHTML

    Markov logic network (MLN) is an important model of statistical relational learning. Learning MLN from data is important in constructing MLN. Real-world data usually contains missing data, learning MLN from missing data is more difficult than learning it from complete data, because we can't compute the exact number of the cases. We put forward a MLN learning algorithm MEM (MLN Expectation Maximiza... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Chinese FrameNet Data in Semantic Web Language

    Publication Year: 2007, Page(s):50 - 55
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (6351 KB) | HTML iconHTML

    The Chinese FrameNet Project is creating a lexical resource for Chinese, based on the principles of Frame Semantics and supported by corpus evidence. The resulting database mainly consists of descriptions of the semantic frames underlying the meanings of the words described and a representative collection of annotated corpus attestations, which jointly exemplify the linking between FEs and their s... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Applying Ontology-based Semantic Measurement for Knowledge Acquisition in Traveling Information System

    Publication Year: 2007, Page(s):56 - 61
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (5479 KB) | HTML iconHTML

    In the theory of knowledge, quantificational measurement of knowledge is of great importance. Meanwhile, how to acquire knowledge automatically has become the bottleneck of ontology-building. In this paper, we first introduce methods of semantic measurement, and propose an algorithm on semantic similarity from the concept of information content of nodes in WordNet. Our method concerns with the pol... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Negative Sentence and "F-V-M" Analysis

    Publication Year: 2007, Page(s):62 - 67
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (6518 KB) | HTML iconHTML

    Although natural language processing (NLP) technology has brought great help to human, it also produces many negative sentences, which has gradually become a big problem to the development of NLP and applications. Now it's an important and urgent task for us to deal with various negative sentences. As a starting study, this paper puts forward a new understanding of the concept of negative sentence... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • SVM-based Hybrid Pattern for New Word Discovery

    Publication Year: 2007, Page(s):68 - 73
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (6854 KB) | HTML iconHTML

    New words bring more challenges into Chinese word segmentation. This paper presents a SVM-based hybrid pattern for new word discovery, trying to integrate the advantages of the statistics-based method and the rule-based method to improve the performance of the new word discovery. In the statistics module, new words discovery is defined as a binary classification problem, in which we considered the... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Recognizing Biomedical Named Entities in the Absence of Human Annotated Corpora

    Publication Year: 2007, Page(s):74 - 81
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (9413 KB) | HTML iconHTML

    Biomedical named entity recognition is an important task in biomedical text mining. Currently the dominant approach is supervised learning, which requires a sufficiently large human annotated corpus for training. In this paper, we propose a novel approach aimed at minimizing the annotation requirement. The idea is to use a dictionary which is essentially a list of entity names compiled by domain e... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Method of Semantic Dictionary Construction from On-line Encyclopedia Classifications

    Publication Year: 2007, Page(s):82 - 89
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (8868 KB) | HTML iconHTML

    This paper introduces a method of constructing a semantic dictionary automatically from the keywords and classify relations of the web encyclopedia Chinese WikiPedia. Semantic units, which are affixes (core/modifier) shared between many phrased-keywords, are selected using statistic method and string affix matching, also with other units to explain the semantic meanings. Then the result are used t... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Rough Concept Recognition Approach for Information Retrieval Based on Latent Semantic Analysis

    Publication Year: 2007, Page(s):90 - 95
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (6140 KB) | HTML iconHTML

    This paper presents an information retrieval approach which uses a rough concept clustering in conjunction with Latent Semantic Analysis(LSA) to provide better document retrieval results matched to queries. The conceptual context defined in this article can be local, so no domain expert has to be involved in this approach. Our experiment consists of word clustering by similarity and rough concept ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Research on Sports Game News Information Extraction

    Publication Year: 2007, Page(s):96 - 101
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (5256 KB) | HTML iconHTML

    With the development of Internet and the development of information technology, a tremendous amount of news information appears everyday. How to extract the useful knowledge is a burning problem. The sports game news-oriented information extraction system introduced in the paper combined the statistics-based hidden Markov model (HMM) and rule-based method based on the technology of natural languag... View full abstract»

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