음성 자료에 대한 규칙 기반 Named Entity 인식 = Rule-based Named Entity (NE) Recognition from Speech

다국어 초록 (Multilingual Abstract)

In this paper, a rule-based (transformation-based) NE recognition system is proposed. This system uses Brill's rule inference approach. The performance of the rule-based system and IdentiFinder, one of most successful stochastic systems, are compared. In the baseline case (no punctuation and no capitalisation), both systems show almost equal performance. They also have similar performance in the case of additional information such as punctuation, capitalisation and name lists. The performances of both systems degrade linearly with the number of speech recognition errors, and their rates of degradation are almost equal. These results show that automatic rule inference is a viable alternative to the HMM-based approach to NE recognition, but it retains the advantages of a rule-based approach.

참고문헌 (Reference)

1 J. Kim, "“Rule based named entity recognition”, (In Technical Report CUED/F-INFENG/TR.385)" Cambridge University Engineering Department 2000

2 E. Brill, "Unsupervised learning of disambiguation rules for part of speech tagging" 1995

3 R. Gaizauskas, "University of Sheffield: description of the LaSIE system as used for MUC-6" 207-220, 1995

4 E. Brill, "Some advances in rule-based part of speech tagging" 722-727, 1994

5 E. Dougherty, "Probability and Statistics for the Engineering, Computing and Physical Sciences" Prentice Hall 1990

6 J. Makhoul, "Performance measures for information extraction" 249-252, 1999

7 B. Sundheim, "Overview of results of the MUC-6 evaluation" 13-31, 1995

8 N. Chinchor, "Overview of MUC-7/MET-2" Proc. 7th Message Understanding Conference

9 J. Fukumoto,F. Masui, "Oki electric industry: description of the Oki system as used for MUC-7" Proc. 7th Message Understanding Conference

10 D. Bikel, "Nymble: a high-performance learning name-finder" 194-201, 1997

11 United States Defense Advanced Research Projects Agency (DARPA), "Named entity task definition" 317-335, 1995

12 D. Appelt, "Named entity extraction from speech: approach and results using the TextPro system" 51-54, 1999

13 D. Miller, "Named entity extraction from broadcast news" 37-40, 1999

14 R. Yangarber,R. Grishman, "NYU: description of the Proteus/PET system as used for MUC-7" Proc. 7th Message Understanding Conference

15 W. Mendeltall, "Mathematical Statistics with Applications" Duxbury Press 1981

16 S. Young, "Large vocabulary continuous speech recognition: a review" 1996

17 D. Palmer, "Information extraction from broadcast news speech data" 41-46, 1999

18 L. Rabiner, "Fundamentals of Speech Recognition" Prentice Hall 1993

19 W. Black,F. Rinaldi,D. Mowatt, "FACILE: description of the NE system used for MUC-7" Proc. 7th Message Understanding Conference

20 S. Katz, "Estimation of probabilities from sparse data for the language model component of a speech recognizer" 35 (35): 400-401, 1998

21 E. Roche,, "Deterministic part-of-speech tagging with finite state transducers" 21 (21): 227-253, 1995

22 H. Chen,Y. Ding, "Description of the NTU system used for MET2" Proc. 7th Message Understanding Conference

23 C. Huyck, "Description of the American university in Cairo's system used for MUC-7" Proc. 7th Message Understanding Conference

24 R. Weischedel, M. Meteer, "Coping with Ambiguity and Unknown Words through Probabilistic Models" 19 (19): 359-382, 1993

25 1998 NIST Hub-4 Information Extraction, "Broadcast News Benchmark Test Evaluation"

26 S. Renals, "Baseline IE-NE experiments using the SPRACH/LASIE system" 47-50, 1999

27 L. Rabiner, "An introduction to hidden Markov model" 3 : 4-16, 1986

28 M. Wightman, "A Stochastic Approach to Named-Entity Extraction" University of Cambridge 1998

29 E. Brill, "A Corpus-Based Approach to Language Learning" University of Pennsylvania 1993

30 M. Przybocki, "1998 Hub-4 information extraction evaluation" 13-18, 1999