Natural Language Processing – IJCNLP 2005: Second International Joint Conference, Jeju Island, Korea, October 11-13, 2005, Proceedings

Front Cover
Robert Dale, Kam-Fai Wong, Jian Su, Oi Yee Kwong
Springer Science & Business Media, Sep 30, 2005 - Computers - 1034 pages
The Theme of IJCNLP 2005: “NLP with Kimchee”, a Conference with a Unique Flavor Welcometo IJCNLP 2005,thesecondannualconferenceof theAsian Federation ofNaturalLanguageProcessing(AFNLP). Followingthesuccessofthe?rstc- ference held in the beautiful cityof Sanya,Hainan Island,China, in March2004, IJCNLP 2005 is held in yet another attractive Asian resort, namely Jeju Island in Korea, on October 11–13, 2005 — the ideal place and season for appreciating mugunghwa, the rose of Sharon, and the national ?ower of Korea. On behalf of the Program Committee, we are excited to present these p- ceedings, which collect together the papers accepted for oral presentation at the conference. We received 289 submissions in total, from 32 economies all over the world: 77% from Asia, 11% from Europe, 0.3% from Africa, 1.7% from Australasia and 10% from North America. We are delighted to report that the popularity of IJCNLP has signi?cantly increased this year, with an increase of 37% from the 211 submissions from 16 economies and 3 continents received for IJCNLP 2004. With such a large number of submissions, the paper selection process was not easy. With the very considerable assistance of our 12 area chairs — Claire Gardent,Jamie Henderson,Chu-Ren Huang,Kentaro Inui, GaryLee, Kim-Teng Lua, Helen Meng, Diego Moll┤ a, Jian-Yun Nie, Dragomir Radev, Manfred Stede, andMing Zhou— andthe 133internationalreviewers,90papers(31%)were- cepted for oral presentation and 62 papers (21%) were recommended as posters.
 

What people are saying - Write a review

We haven't found any reviews in the usual places.

Contents

A New Method for Sentiment Classification in Text Retrieval
1
Topic Tracking Based on Linguistic Features
10
The Use of Monolingual Context Vectors for Missing Translations in CrossLanguage Information Retrieval
22
Automatic Image Annotation Using Maximum Entropy Model
34
CorpusBased Analysis of Japanese Relative Clause Constructions
46
Parsing Biomedical Literature
58
Parsing the Penn Chinese Treebank with Semantic Knowledge
70
Using a Partially Annotated Corpus to Build a Dependency Parser for Japanese
82
WebBased Unsupervised Learning for Query Formulation in Question Answering
519
A Chunking Strategy Towards Unknown Word Detection in Chinese Word Segmentation
530
A LexiconConstrained Character Model for Chinese Morphological Analysis
542
A Study of VerbNoun VN Collocations
553
Automatic Extraction of Fixed Multiword Expressions
565
A Level of Detail Approach
576
Why Is Zero Marking Important in Korean?
588
A PhraseBased ContextDependent Joint Probability Model for Named Entity Translation
600

An Experiment Using a Web Search Engine
93
Automatic Discovery of Attribute Words from Web Documents
106
Paraphrase Acquisition Across the Web
119
Confirmed Knowledge Acquisition Using Mails Posted to a Mailing List
131
Automatic Partial Parsing Rule Acquisition Using Decision Tree Induction
143
Chunking Using Conditional Random Fields in Korean Texts
155
High Efficiency Realization for a WideCoverage Unification Grammar
165
LinguisticallyMotivated Grammar Extraction Generalization and Adaptation
177
PPAttachment Disambiguation Boosted by a Gigantic Volume of Unambiguous Examples
188
Adapting a Probabilistic Disambiguation Model of an HPSG Parser to a New Domain
199
A Hybrid Approach to Single and Multiple PP Attachment Using WordNet
211
Period Disambiguation with Maxent Model
223
Acquiring Synonyms from Monolingual Comparable Texts
233
A Method of Recognizing Entity and Relation
245
Inversion Transduction Grammar Constraints for Mining Parallel Sentences from QuasiComparable Corpora
257
Automatic Term Extraction Based on Perplexity of Compound Words
269
Document Clustering with Grouping and Chaining Algorithms
280
Using Multiple Discriminant Analysis Approach for Linear Text Segmentation
292
Classifying Chinese Texts in Two Steps
302
Assigning Polarity Scores to Reviews Using Machine Learning Techniques
314
Abstraction with HowNet Semantics
326
PLSI Utilization for Automatic Thesaurus Construction
334
Analysis of an Iterative Algorithm for TermBased Ontology Alignment
346
Finding Taxonomical Relation from an MRD for Thesaurus Extension
357
Relation Extraction Using Support Vector Machine
366
Discovering Relations Between Named Entities from a Large Raw Corpus Using Tree SimilarityBased Clustering
378
Automatic Relation Extraction with Model Order Selection and Discriminative Label Identification
390
Mining InterEntity Semantic Relations Using Improved Transductive Learning
402
A Preliminary Work on Classifying Time Granularities of Temporal Questions
414
Classification of MultipleSentence Questions
426
A Rule Based Syllabification Algorithm for Sinhala
438
An Ensemble of Grapheme and Phoneme for Machine Transliteration
450
Improving Statistical Word Alignment with Ensemble Methods
462
Empirical Study of Utilizing MorphSyntactic Information in SMT
474
InstanceBased Generation for Interactive Restricted Domain Question Answering Systems
486
Answering Definition Questions Using Web Knowledge Bases
498
Exploring Syntactic Relation Patterns for Question Answering
507
Machine Translation Based on ConstraintBased Synchronous Grammar
612
A Machine Learning Approach to Sentence Ordering for Multidocument Summarization and Its Evaluation
624
Significant Sentence Extraction by Euclidean Distance Based on Singular Value Decomposition
636
TwoPhase Biomedical Named Entity Recognition Using A Hybrid Method
646
Heuristic Methods for Reducing Errors of Geographic Named Entities Learned by Bootstrapping
658
Building a JapaneseChinese Dictionary Using KanjiHanzi Conversion
670
Automatic Acquisition of Basic Katakana Lexicon from a Given Corpus
682
A Chinese Temporal Parser for Extracting and Normalizing Temporal Information
694
FrenchEnglish Terminology Extraction from Comparable Corpora
707
A TwinCandidate Model of Coreference Resolution with NonAnaphor Identification Capability
719
Improving Korean Speech Acts Analysis by Using Shrinkage and Discourse Stack
731
Anaphora Resolution for Biomedical Literature by Exploiting Multiple Resources
742
Automatic Slide Generation Based on Discourse Structure Analysis
754
Using the Structure of a Conceptual Network in Computing Semantic Relatedness
767
Semantic Role Labelling of Prepositional Phrases
779
Global PathBased Refinement of Noisy Graphs Applied to Verb Semantics
792
Semantic Role Tagging for Chinese at the Lexical Level
804
Detecting Article Errors Based on the Mass Count Distinction
815
Principles of Nonstationary Hidden Markov Model and Its Applications to Sequence Labeling Task
827
Integrating Punctuation Rules and Na´ve Bayesian Model for Chinese Creation Title Recognition
838
A Connectionist Model of Anticipation in Visual Worlds
849
Automatically Inducing a PartofSpeech Tagger by Projecting from Multiple Source Languages Across Aligned Corpora
862
The Verbal Entries and Their Description in a Grammatical InformationDictionary of Contemporary Tibetan
874
A Case Study
885
Parameterised Versus ParameterFree
896
Exploiting Lexical Conceptual Structure for Paraphrase Generation
908
Word Sense Disambiguation by Relative Selection
920
Towards Robust High Performance Word Sense Disambiguation of English Verbs Using Rich Linguistic Features
933
Automatic Interpretation of Noun Compounds Using WordNet Similarity
945
An Empirical Study on Language Model Adaptation Using a Metric of Domain Similarity
957
A Comparative Study of Language Models for Book and Author Recognition
969
Lexical Choice via Topic Adaptation for Paraphrasing Written Language to Spoken Language
981
A CaseBased Reasoning Approach for Speech Corpus Generation
993
WebBased Terminology Translation Mining
1004
Extracting Terminologically Relevant Collocations in the Translation of Chinese Monograph
1017
Author Index
1029
Copyright

Other editions - View all

Common terms and phrases