Multilingual and Mixed Language Named Entity Recognition:

Combining Statistical and Symbolic Models

Workshop Program

July 12, 2003

 

 

Session 1: Trainable systems

09:00         Youzheng Wu, Jun Zhao, Bo Xu

Chinese Named Entity Recognition Combining Statistical Model and Human Knowledge

09:30         Kuniko Saito and Masaaki Nagata

Multi-Language Named-Entity Recognition System based on HMM

10:00         Hsin-Hsi Chen, Changhua Yang, Ying Lin

Learning Formulation and Transformation Rules for Multilingual Named Entities

 

10:30-11:00     Coffee break

 

Session 2: Summary of available resources

11:00         Stephanie Strassel and Alexis Mitchell

Multilingual Resources for Entity Extraction

 

Invited Talk

11:30         David Yarowsky

Bootstrapping Multilingual Named-Entity Recognizers

 

12:30-14:00     Lunch: (sponsored by Microsoft Natural Language Group)

 

Session 3: Using available resources

14:00         Diana Maynard, Valentin Tablan, Hamish Cunningham

NE Recognition Without Training Data on a Language You Don’t Speak

 

14:30         Lluís Màrquez, Adrià de Gispert, Xavier Carreras and Lluís Padró

Low-cost Named Entity Classification for Catalan: Exploiting Multilingual Resources and Unlabeled Data

 

Session 4: Alignment for resource creation

15:00         Tadashi Kumano, Hideki Kashioka, Hideki Tanaka and Takahiro Fukusima

Construction and Analysis of Japanese-English Broadcast News Corpus with Named Entity Tags

 

15:30-16:00 Coffee break

 

Session 4 (continued)

16:00         Fei Huang, Stephan Vogel and Alex Waibel

Automatic Extraction of Named Entity Translingual Equivalence Based on Multi-Feature Cost Minimization

     

16:30         Paola Virga and Sanjeev Khudanpur

Transliteration of Proper Names in Cross-Language Information Retrieval