论文信息 - Polish N-Grams and Their Correction Process

Polish N-Grams and Their Correction Process

Word n-gram statistics collected from over 1 300 000 000 words are presented. Eventhough they were collected from various good sources, they contain several types of errors. The paper focuses on the process of partly supervised correction of the n- grams. Types of errors are described as well as our software allowing efficient and fast corrections.

[1] Steve Young,et al. The HTK book , 1995 .

[2] James H. Martin,et al. Speech and language processing: an introduction to natural language processing, computational linguistics, and speech recognition, 2nd Edition , 2000, Prentice Hall series in artificial intelligence.

[3] Gregory D. Abowd,et al. Human-Computer Interaction (3rd Edition) , 2003 .

[4] Richard Lippmann,et al. Neural Net and Traditional Classifiers , 1987, NIPS.

[5] Mikko Kurimo,et al. Importance of High-Order N-Gram Models in Morph-Based Speech Recognition , 2009, IEEE Transactions on Audio, Speech, and Language Processing.

[6] Gregory D. Abowd,et al. Human-Computer Interaction, third edition , 2004 .

[7] Manfred K. Warmuth,et al. THE CMU SPHINX-4 SPEECH RECOGNITION SYSTEM , 2001 .

[8] Yvonne Rogers,et al. Interaction Design: Beyond Human-Computer Interaction. Second Edition , 2007 .

[9] Jun Wu,et al. A maximum entropy language model integrating N-grams and topic dependencies for conversational speech recognition , 1999, 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. ICASSP99 (Cat. No.99CH36258).

[10] Yvonne Rogers,et al. Interaction Design: Beyond Human-Computer Interaction , 2002 .

[11] Philip C. Woodland,et al. Language modelling for Russian and English using words and classes , 2003, Comput. Speech Lang..