Sighan 2003

14 papers

Top Research Directions

The 26 research directions with Sighan 2003 papers, ranked by paper count. Share is the fraction of the edition’s papers in the direction.

#DirectionPapersShare
1Processing Text with Implicit Word Boundaries857.1%
2Open Vocabulary Recognition for Spoken Language Systems214.3%
3Advanced Aggregation and Selection for Model Ensembles17.1%
4Algorithmic Quantification of Speech Rhythm17.1%
5Cross-Lingual Transfer for Low-Resource Dependency Parsing17.1%
6Decoupled Modular Frameworks for Rapid Scientific Experimentation17.1%
7Dynamic Interpolation for Contextual Language Modeling17.1%
8Evolutionary Weight Optimization17.1%
9Hybrid Word and Sub-word Modeling for Open Vocabulary Systems17.1%
10Integrating Symbolic Rules and Statistical Language Models17.1%
11Iterative Guideline Refinement for Data Annotation17.1%
12Managing the Precision Recall Tradeoff in Information Extraction17.1%
13Measuring Inter-Annotator Agreement for Reliable Data Curation17.1%
14Mitigating Statistical Co-occurrence Noise in Text Mining17.1%
15Morphological Realization for Inflected Languages17.1%
16Multi-Factor Sentence Ranking for Extractive Summarization17.1%
17Overcoming Cascading Errors from Automated Word Segmentation17.1%
18Overcoming Data Sparsity in Statistical Language Models17.1%
19Overcoming the Coverage Limitations of Formal Grammars17.1%
20Overcoming the Data Annotation Bottleneck in Language Processing17.1%
21Phrase Level Simplification of Multi Word Expressions17.1%
22Resolving Structural Ambiguity in Natural Language Parsing17.1%
23Resolving Text Ambiguity with Longest Match Heuristics17.1%
24Restoring Structure and Punctuation in Speech Transcripts17.1%
25Statistical Association Measures for Lexical and Semantic Discovery17.1%

Download all directions as CSV

Institutions

Institutions credited by Sighan 2003 papers: a paper credits every institution named in its affiliations, once. 12 institutions share 12 credited papers.

#InstitutionPapersShare
1Institute for Computational Linguistics "A. Zampolli" 325.0%
2Peking University 325.0%
3Chinese Academy of Sciences 216.7%
4Institute of Information Science, Academia Sinica 216.7%
5Microsoft (United States) 216.7%
6Microsoft Research Asia (China) 216.7%
7Tsinghua University 216.7%
8Hong Kong Polytechnic University 18.3%
9State Key Laboratory of Pattern Recognition 18.3%
10University of Colorado Boulder 18.3%
11University of Hong Kong 18.3%
12University of Science and Technology of China 18.3%

Download all institutions as CSV

About this data

Papers. Sighan 2003 lists 14 papers on Lacuna, duplicate versions counted once; rejected and withdrawn submissions are left out.

Directions. Directions are Lacuna’s clustering of the concept elements extracted from each paper, so a paper can belong to several and direction counts add up to more than the paper count. A direction’s share is its papers divided by the edition’s papers.

Institutions. A paper credits each institution named in its affiliations, resolved to a ROR record, once. 12 of 14 papers (85.7%) credit at least one institution and are the base for institution shares; the rest have no resolved affiliation yet.

Data. Counts come from Lacuna’s data build of 2026-11-19 and change as papers are added. Tables as CSV: directions · institutions. Cite as: Lacuna, “Sighan 2003”, https://lacuna.tiptreesystems.com/venue/sighan/2003.

Top Authors

AuthorPapers
Jianfeng Gao2
Qun Liu2
Wei-Yun Ma2
Dan Jurafsky1
Deyi Xiong1
Guohong Fu1
Hao Zhang1
Houfeng Wang1
Juanzi Li1
Maosong Sun1
Xueqi Cheng1

Impactful Papers

Papers from Sighan 2003 that shaped research clusters.

Foundational

Influential

Papers

Title
A Bottom-up Merging Algorithm for Chinese Unknown Word Extraction
A Two-stage Statistical Word Segmentation System for Chinese
A Unicode Based Adaptive Segmentor
Building a Large Chinese Corpus Annotated with Semantic Dependency
Chinese Lexical Analysis Using Hierarchical Hidden Markov Model
Chinese Word Segmentation at Peking University
HHMM-based Chinese Lexical Analyzer ICTCLAS
Introduction to CKIP Chinese Word Segmentation System for the First International Chinese Word Segmentation Bakeoff
News-Oriented Automatic Chinese Keyword Indexing
Single Character Chinese Named Entity Recognition
The Effect of Rhythm on Structural Disambiguation in Chinese
Two-Character Chinese Word Extraction Based on Hybrid of Internal and Contextual Measures
Unsupervised Training for Overlapping Ambiguity Resolution in Chinese Word Segmentation
Utterance Segmentation Using Combined Approach Based on Bi-directional N-gram and Maximum Entropy