Automatic event generation from multi-lingual news stories

ABSTRACT

We propose a novel approach for automatic generation of topically-rela ted events from multi-lingual news sources. Named entity terms are extracted automatically from the news content. Together with the content terms, they constitute the basis of representing the story. We employ transformation-based linguistic tagging approach for named entity extraction. Two methods of gross translation on Chinese story representation into English have been implemented. The first approach uses only a bilingual dictionary. The second method makes use of a parallel corpus as an additional resource. Unsupervised learning is employed to discover the events.

REFERENCES

• 1: http://morph.ldc.upenn.edu/TDT Linguistic Data Consortium
• 2: Eric Brill, Transformation-based error-driven learning and natural language processing: a case study in part-of-speech tagging, Computational Linguistics, v.21 n.4, p.543-565, December 1995
• 3: C.W. Ip. Transformational Tagging for Topic Tracking in Natural Language. In Dept. of Systems Engg. & Engg Mngt of CUHK Master Thesis, June 2000.
• 4: H. Meng and C.W. Ip. An Analytical Study of Transformational Tagging for Chinese Text. In Proceedings of Research on Computational Linguistics Conference (ROCLING XII), Taipei, Taiwan, ROC,pages 101-122, 1999.
• 5: The Year 2000 Topic Detection and Tracking (TDT2000) Task Definition and Evaluation Plan.

INDEX TERMS

Primary Classification:
  H. Information Systems
  H.3 INFORMATION STORAGE AND RETRIEVAL

Additional Classification:
  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE
      I.2.7 Natural Language Processing
          Subjects: Machine translation

General Terms:
Design, Documentation, Human Factors, Languages, Management, Measurement, Performance, Theory

Keywords:
event detection, event discovery, multilingual text processing