东方语言计算机处理，东方以远：未来挑战研究/会议录LNCS-4285:Computer processing of Oriental languages

This book constitutes the thoroughly refereed proceedings of the 21st International Conference on Computer Processing of Oriental Languages, ICCPOL 2006, held in Singapore in December 2006, colocated with ISCSLP 2006, the 5th International Symposium on Chinese Spoken Language Processing.
　　The 36 revised full papers and 20 revised short papers presented were carefully reviewed and selected from 169 submissions. The papers are organized in topical sections on information retrieval, document classification, questions and answers, summarization, machine translation, word segmentation, chunking, abbreviation expansion, writing-system issues, parsing, semantics, and lexical resources.

The LNAI series reports state-of-the-art results in artificial intelligence re-search，development，and education，at a high level and in both printed and electronic form. Enjoying tight cooperation with the R＆D community，with numerous individuals，as well as with prestigious organizations and societies，LNAI has grown into the most comprehensive artificial intelligence research forum available.
The scope of LNAI spans the whole range of artificial intelligence and intelli-gent information processing including interdisciplinary topics in a variety of
application fields. The type of material published traditionally includes
proceedings（published in time for the respective conference）
post-proceedings（consisting of thoroughly revised final full papers）
research monographs（which may be based on PhD work）

Information Retrieval/Document Classification/QA/　Summarization I
　Answering Contextual Questions Based on the Cohesion　with Knowledge
　Segmentation of Mixed Chinese/English Document Including Scattered　Italic Characters
　Using Pointwise Mutual Information to Identify Implicit Features　in Customer Reviews
　Using Semi-supervised Learning for Question Classification
　Query Similarity Computing Based on System Similarity　Measurement
Machine Translation I
　An Improved Method for Finding Bilingual Collocation Correspondences　from Monolingual Corpora
　A Syntactic Transformation Model for Statistical Machine　Translation
　Word Alignment Between Chinese and Japanese Using Maximum　Weight Matching on Bipartite Graph
　Improving Machine Transliteration Performance by Using Multiple　Transliteration Models
　Information Retrieval/Document Classification/ QA/Summarization II
　Clique Percolation Method for Finding Naturally Cohesive and Overlapping Document Clusters
　Hybrid Approach to Extracting Information from Web-Tables
　A Novel Hierarchical Document Clustering Algorithm Based on a kNN Connection Graph
Poster Session 1
　The Great Importance of Cross-Document Relationships　for Multi-document Summarization
　The Effects of Computer Assisted Instruction to Train People　with Reading Disabilities Recognizing Chinese Characters
　Discrimination-Based Feature Selection for Multinomial Na'/ve Bayes　Text Classification
　A Comparative Study on Chinese Word Clustering
　Populating FrameNet with Chinese Verbs Mapping Bilingual　Ontological WordNet with FrameNet
　Collecting Novel Technical Terms from the Web by Estimating Domain　Specificity of a Term
　Building Document Graphs for Multiple News Articles Summarization:　An Event-Based Approach
　A Probabilistic Feature Based Maximum Entropy Model for Chinese　Named Entity Recognition
……
Word Segmentation/Chunking/Abbreviation/Expansion/Witritng -System Issues
Machine TranlationII
Poster Session2
Parsing/Semantics/Lexical Resources
Author Index