Selected Publications (by topic)

[ Alignment | Term Extraction | Pronunciation & Accent Modeling | Spoken Language & Multilingual Processing | Robust Speech Recognition ]

Alignment

[ Finding bilingual (aka trans-lingual, cross-lingual) term, word, POS, and sense correspondences using corpora. ]

• Dekai Wu and Pascale Fung, “Can Semantic Role Labeling Improve SMT? “, in Proceedings of the Annual Conference of European Association of Machine Translation 2009, 2009.
• Dekai Wu and Pascale Fung, “Semantic Roles for SMT: A Hybrid Two-Pass Model”, in Proceedings of the Joint Conference of the North American Chapter of ACL/Human Language Technology, 2009.
• Pascale Fung, Zhaojun Wu, Yongsheng Yang and Dekai Wu. "Learning Bilingual Semantic Frames: Shallow Semantic Parsing vs. Semantic Role Projection". In 11th Conference on Theoretical and Methodological Issues in Machine Translation (TMI 2007). Skovde, Sweden: Sep 2007. 75-84.
• Pascale Fung, Zhaojun Wu, Yongsheng Yang, Dekai Wu, “Automatic Learning of Chinese/English Semantic Structure Mapping.”  In IEEE/ACL 2006 Workshop on Spoken Language Technology (SLT 2006). Aruba: Dec 2006. 230-233.  
• Pascale Fung and Benfeng Chen, “Robust Word Sense Translation by EM Learning of Frame Semantics”. In Proceeedings of ACL/COLING 2006, Sydney, Australia. Pp 239-246. July 2006.
• Marine Carpuat, Pascale Fung and Grace Ngai, “Aligning Word Senses Using Bilingual Corpora”. In ACM Transaction on Asian Language and Information Processing. Volume 5, Issue 2 Pp: 89 – 120, June 2006.
• Dekai Wu and Pascale Fung, "Inversion Transduction Grammar Constraints for Mining Parallel Sentences from Quasi-Comparable Corpora". In Proceedings of the 2nd International Joint Conference on Natural Language Proceedings (IJCNLP 05). October 2005. Jeju Island, Korea.
• Pascale Fung and Benfeng Chen, "BiFrameNet: bilingual Frame Semantics Resource Construction by Cross-lingual Induction", in Proceedings of the 20th International Conference on Computational Linguistics (COLING 2004), Geneva, Switzerland, August 2004
• Pascale Fung and Percy Cheung, "Multi-level Bootstrapping for Extracting Parallel Sentences from a Quasi-comparable Corpora", in Proceedings of the 20th International Conference on Computational Linguistics (COLING 2004), Geneva, Switzerland, August 2004
• Benfeng Chen and Pascale Fung, "Automatic Construction of an English-Chinese Bilingual FrameNet", in Processings of Human Language Technology Conference 2004 (HLT/NAACL-04), Boston, Mass, May 2004
• Pascale Fung and Percy Cheung, "Mining Very-Non-Parallel Corpora: Parallel Sentence and Lexicon Extraction via Bootstrapping and EM". In Proceedings of EMNLP 2004, Barcelona, Spain: July 2004
• Percy Cheung and Pascale Fung, "Sentence Alignment in Parallel, Comparable, and Quasi-comparable Corpora". In LREC 2004, Lisbon, Portugal: May 2004
• Grace Ngai, Marine Carpuat and Pascale Fung, "Identifying Concepts Across Languages: A First Step towards a Corpus-based Approach to Automatic Ontology Alignment". In Proceedings of COLING-02, Taipei, Taiwan: 24th Aug-1st Sept, 2002
• Marine Carpuat, Grace Ngai, Pascale Fung and Kenneth Church, "Creating a Bilingual Ontology: A Corpus-Based Approach for Aligning WordNet and HowNet",  In Proceedings of the 1st Global WordNet Conference, Mysore, India: Jan 2002
• Wong, Ping-Wai and Pascale Fung (2002) "Nouns in WordNet and HowNet: an Analysis and Comparison of Semantic Relations", in Proceedings of the 1st International Conference on Global WordNet, 21st-25th, Mysore, India, pp. 319-322: Jan 2002
• Pascale Fung, "A Statistical View on Bilingual Lexicon Extraction-From Parallel Corpora to Non-parallel Corpora", In Parallel Text Processing: Alignment and Use of Translation Corpora, Kluwer 2000
• Pascale Fung and Lo, Yuen Yee, "An IR Approach for Translating New Words from Nonparallel, Comparable Texts". In Proceedings of COLING-ACL98, Montreal, Canada: Aug. 1998, 414-420.
• Pascale Fung and Kathleen McKeown, "Finding Terminology Translations from Non-parallel Corpora", in The 5th Annual Workshop on Very Large Corpora, Hong Kong: Aug 1997, 192--202
• Pascale Fung, "Domain Word Translation by Space-Frequency Analysis of Context Length Histograms", In ICASSP '96: International Conference on Acoustics, Signal and Speech Processing, Atlanta, Georgia: May 1996, vol. I, 184--187.
• Pascale Fung and Kathleen McKeown, "A Technical Word and Term Translation Aid using Noisy Parallel Corpora Across Language Groups", In The Machine Translation Journal, Special Issue on New Tools for Human Translators, 1996, 53-87
• Pascale Fung, "A Pattern Matching Method for Finding Noun and Proper Noun Translations from Noisy Parallel Corpora", In 33rd Annual Conference of the Association for Computational Linguistics, Boston, Massachusetts: Jun.  1995, 236--233.
• Pascale Fung, "Compiling Bilingual Lexicon Entries from a Non-Parallel English-Chinese Corpus", In Third Annual Workshop on Very Large Corpora, Boston, Massachusetts: Jun. 1995, 173--183.
• Pascale Fung and WU Dekai "Coerced Markov Models for Cross-lingual Lexical-Tag Relations", In Sixth International Conference on Theoretical and Methodological Issues in Machine Translation, Leuven, Belgium: Jul. 1995, 240--255.
• Pascale Fung and Kathleen McKeown, "Aligning Noisy Parallel Corpora across Language Groups: Word Pair Feature Matching by Dynamic Time Warping", In AMTA-94: Association of Machine Translation in the Americas, Columbia, Maryland: Oct. 1994, 81--88.
• WU Dekai and Pascale Fung, "Improving Chinese Tokenization with Linguistic Filters on Statistical Lexical Acquisition", In ANLP-94: 4th Conference on Applied Natural Language Processing, Stuttgart: Oct. 1994, 180--181.
• Pascale Fung and Kenneth CHURCH, "K-vec: A New Approach for Aligning Parallel Texts". In COLING-94: 15th International Conference on Computational Linguistics, Kyoto: Aug. 1994, 1096--1102.
• K. Church, I. Dagan, W. Gale, Pascale Fung, J. Helfman, B. Satish, "Aligning Parallel Texts: Do Methods Developed for English-French generalize to Asian Languages?" In PACFoCoL-93: Pacific Asia Conference on Formal and Computational Linguistics, Taipei: Aug. 1993.

Term Extraction ( from Texts and Speech)

• Lufeng Zhai, Pascale Fung, Richard Schwartz, Marine Carpuat and Dekai Wu, "Using N-best Lists for Named Entity Recognition from Chinese Speech", in Proceedings of Human Language Technology Conference 2004 (HLT/NAACL-04), Boston, Mass, May 2004
• Pascale Fung, "Extracting Key Terms from Chinese and Japanese texts", In International Journal on Computer Processing of Oriental Languages, Special Issue on Information Retrieval on Oriental Languages, 1998, 99-121
• Pascale Fung and Wu, Dekai, “Statistical Augmentation of a Chinese Machine-Readable Dictionary”. In Natural Language Processing Using Very Large Corpora, Kluwer 1997
• Pascale Fung, Min-yen Kan, and Yurie Horita, "Extracting Japanese Domain and Technical Terms is Relatively Easy", In Second International Conference in New Methods for Language Processing, Bilkent, Turkey: Sep. 1996, 148--159.

Pronunciation and Accent Modeling

• Pascale Fung, "Spontaneous and Accented Mandarin Speech Recognition". In Advances in Chinese Spoken Language Processing. World Scientific 2007.
• Liu, Yi and Pascale Fung, "Multi-Accent Chinese Speech Recognition". In INTERSPEECH 2006, Pittsburgh, September 2006.
• Pascale Fung and Yi Liu, "Effects and Modeling of Phonetic and Acoustic Confusions in Accented Speech". In the Journal of the Acoustical Society of America, Vol.118, Issue 5, pp.3279 - 3293, Nov. 2005.
• LIU Yi and Pascale Fung, "Acoustic and Phonetic Confusions in Accented Speech Recognition". In INTERSPEECH'2005 - EUROSPEECH, Lisbon, September 4-8 2005.
• Yi Liu, Pascale Fung, Christopher Cieri, Yongsheng, Yang and Shudong Huang, "EARSCTS: A Chinese Telephony Conversational Corpus for Speech Processing", In Technical Acoustics, Vol. 24, pp.486 - 489, 2005
• Yi, Liu, Pascale Fung, Shudong Huang, Chris Cieri, "Development of a Chinese telephony conversational corpus for speech processing", in Proceedings of ISCSLP 2004, Dec 2004.
• Liu, Yi and Pascale Fung, "State-dependent phonetic tied mixtures with pronunciation modeling for spontaneous speech recognition", In IEEE Transactions on Speech and Audio Processing, Vol 12, no. 4, pp 351-364, July 2004
• Liu, Yi and Pascale Fung, "Pronunciation modeling for spontaneous Mandarin speech recognition", International Journal of Speech Technology, Vol. 7, No. 2, pp. 155-172, Apr 2004
• Liu, Yi and Pascale Fung, "Partial change accent models for accented Mandarin speech recognition", in Proceedings of the IEEE Workshop on Automatic Speech Recognition and Understanding, St. Thomas, U.S. Virgin Islands, Dec 2003
• Liu, Yi and Pascale Fung, "Modeling Partial Pronunciation Variations for Spontaneous Mandarin Speech Recognition" In Computer Speech & Language, Vol. 17, No. 4, pp. 357-379, Oct 2003
• Liu, Yi and Pascale Fung, "Automatic phone set extension with confidence measure for spontaneous speech". In EUROSPEECH '03, Geneva, September 2003
• Pascale Fung and Yi Liu, "Triphone Model Reconstruction for Mandarin Pronunciation Variations", in Proceedings of the IEEE International Conference on Acoustic, Speech and Signal, Hong Kong, April 2003
• Liu, Yi and Pascale Fung, "Model Partial Pronunciation Variations for Spontaneous Mandarin Speech Recognition", ICSLP 2002, Denver, Colorado: Sept 2002
• Liu, Yi and Pascale Fung, "Partial Change Phone Models for Pronunciation Variations in Spontaneous Mandarin Speech", ISCSLP 2002, Taipei, Taiwan: August 2002
• Zheng Fang, Song Zhanjiang, Pascale Fung, William J. Byrne, "Mandarin Pronunciation Modeling Based on CASS Corpus" In  Journal of Computer Science and Technology, Vol. 17, No. 3, pp 249-263, 2002
• Fang Zheng, Zhanjiang Song, Pascale Fung, William Byrne, "Modeling Pronunciation Variation Using Context-Dependent Weighting and B/S Refined Acoustic Modeling", EuroSpeech, 1:57-60, Sept. 3-7, 2001, Aalborg, Denmark
• W. Byrne, B. Venkataramani, T. Kamm, T.F. Zheng, Z. Song, Pascale Fung, LIU Yi, U Ruhi, "Automatic Generation of Pronunciation Lexicons for Mandarin Spontaneous Speech", ICASSP 2001, Salt Lake City: May 2001
• Liu, Yi and Pascale Fung, W. Byrne, R. Umar, "Pronunciation Modeling Of Spontaneous Mandarin Speech Using Phonetic Feature Distance And Optimal Gaussian Mixture Sharing", ICASSP 2001, Salt Lake City: May 2001
• Liu, Yi and Pascale Fung, "Estimating Pronunciation Variations from Acoustic Likelihood Score for HMM Reconstruction.", Eurospeech 2001, Aalborg, Denmark: Sept 2001
• Fang Zheng, Zhanjiang Song, Pascale Fung, and William Byrne, "Mandarin pronunciation modeling based on CASS corpus", Sino-French Symposium on Speech and Language Processing, pp. 47-53, Oct. 16, 2000, Beijing
• Liu, Wai Kat and Pascale Fung, "MLLR-based accent model adaptation without accented data", ICSLP 2000, Beijing, China: Oct 2000
• Liu, Yi and Pascale Fung , "Modeling Pronunciation Variations in Spontaneous Mandarin Speech", ICSLP 2000, Beijing, China: Oct 2000
• Liu, Yi and Pascale Fung, "Rule-Based Word Pronunciation Networks Generation for Mandarin Speech Recognition", ISCSLP 2000, Beijing, China: Oct 2000
• Pascale Fung and LIU Wai Kat, "Fast Accent Identification and Accented Speech Recognition", ICASSP 99: International Conference on Acoustics, Signal and Speech Processing, Phoenix, Arizona: March 1999
• Pascale Fung, MA Chi Yuen, and LIU Wai Kat, "MAP-based Cross-Language Adaptation Augmented by Linguistic Knowledge: from English to Chinese", EUROSPEECH 99, Budapest, Hungary: September 1999

Spoken Language and Multilingual Processing

• Zhang, J., and Pascale Fung, “Extractive Speech Summarization Using Shallow Rhetorical Structure Modeling”, To appear in IEEE Transactions on Audio,Speech and Language Processing, 2009
• Zhang, J., and Pascale Fung, “Active Learning of Extractive Reference Summaries for Lecture Speech Summarization”, In 2nd Workshop on Building and Using Comparable Corpora (BUCC 2009): from parallel to non-parallel corpora, ACL-IJCNLP 2009, Suntec, Singapore, Auguest 2009
• Pascale Fung, Zhang, J., Chan, H.Y., and Huang, S.L., “Rhetorical Structure Modeling for Lecture Speech Summarization”, in 2009 Annual Summit and Conference of the Asia Pacific Signal and Information Processing Association (APSIPA), Sapporo, Japan, October 2009
• Justin Jian Zhang, Shilei Huang, and Pascale Fung, “RSHMM++ for extractive lecture speech summarization”, in IEEE/ACL Spoken Language Technology Workshop, 2008. SLT 2008, pages 161–164.
• Pascale Fung and Tanja Shultz, “Multilingual Spoken Language Processing”. In IEEE Signal Processing Magazine, May 2008.
• Pascale Fung, Ho Yin Chan and Jian Zhang, “Rhetorical-state Hidden Markov Models for Extractive Speech Summarization” in ICASSP 2008, 2008.
• Ho Yin Chan, Jian Zhang, Pascale Fung and Lu Cao, “A Mandarin Lecture Speech Transcription System for Speech Summarization” ASRU 2007, 2007.
• Jian Zhang, Ho Yin Chan, and Pascale Fung, “Improving Lecture Speech Summarization using Rhetorical Information” ASRU 2007, 2007.
• Jian Zhang, Ho Yin Chan, Pascale Fung and Lu Cuo, “A Comparative Study on Speech Summarization of Broadcast News and Lecture Speech” in Proc. Interspeech 2007, 2007.
• Jian Zhang and Pascale Fung, “Speech summarization without Lexical Features for Mandarin Broadcast News” in Proc. NAACL/HLT 2007, 2007.
• Pascale Fung, Zhaojun Wu, Yongsheng Yang and Dekai Wu. "Learning Bilingual Semantic Frames: Shallow Semantic Parsing vs. Semantic Role Projection".  11th Conference on Theoretical and Methodological Issues in Machine Translation (TMI 2007). Skovde, Sweden: Sep 2007. 75-84.
• Pascale Fung and Grace Ngai, "One Story One Flow: Hidden Markov Story Models for Multilingual and Multi-document Summarization".  In ACM Transaction on Speech and Language Processing.  Volume 3,  Issue 2, pp 1 - 16, July 2006.
• Percy Cheung and Pascale Fung, "Translation Disambiguation in Mixed Language Queries". In Machine Translation Journal, (2005) 18:273-251.
• Chao Xu, Yi Liu, Yongsheng Yang, Pascale Fung, and Zhigang Cao, "A system for Mandarin short phrase recognition on portable devices", in Proceedings of ISCSLP 2004, Dec 2004.
• Pascale Fung, Grace Ngai, Yongsheng Yang, and Benfeng Chen, "A Maximum Entropy Chinese Parser Augmented with Transformation-Based Learning", in ACM Transaction on Asian Language Processing. Volume 3 Issue 2, pp 159 - 168, June 2004.
• Pascale Fung and LIU Yi, "A Grammar-Based Chinese to English Speech Translation System for Portable Devices", in proceedings of The 7th International Conference on Spoken Language Processing, Jeju Island, Korea Oct 2004
• Cheung, Chi Shun and Pascale Fung, "Unsupervised Learning of a Chinese Spontaneous and Colloquial Speech Lexicon with Content and Filler Phrase Classification", In International Journal of Speech Technology, Vol. 7, No. 2, pp 173-178, Apr 2004
• Pascale Fung, Grace Ngai, and Percy Cheung, "Combining optimal clustering and hidden Markov models for extractive summarization", in Proceedings of ACL Workshop on Multilingual Summarization, 2003, pp. 29-36
• Li Aijun, Zheng Fang, William Byrne, Pascale Fung, "CASS: A Phonetically Transcribed Corpus of Mandarin Spontaneous Speech", International Conference on Spoken Language Processing, pp. I-485~488, Oct. 16-20, 2000, Beijing
• Tsoi, Pang Kuen and Pascale Fung, "A LLR-Based Technique for Frame Selection for GMM-based text-independent Speaker Recognition", ICSLP 2000, Beijing, China: Oct 2000
• Tang, Haijiang and Pascale Fung, "A Multi-Path Syllable to word decoder with Language Model Optimization and Automatic Lexicon Augmentation", ICSLP 2000, Beijing, China: Oct 2000
• Ye, Hui and Pascale Fung, "Principal mixture speaker adaptation for improved continuous speech recognition", ICSLP 2000, Beijing, China: Oct 2000
• Amelie PLU, MA Chi Yuen and Pascale Fung , "SALSA Version 3.0:  A Single Recognizer-based Multilingual Speech-based Web Browser", RIAO 2000, Paris, France: April 2000
• Pascale Fung and Lo, Yuen Yi, "Understanding Chinese Spontaneous Speech - Are Mandarin and Cantonese Very Different?" In Proceedings of ISSPIS 99, Guangzhou, China, November 1999.
• CHEUNG Chi Shun and Pascale Fung, "Keyword / Fillerword Modeling for Spontaneous Spoken Mixed Language Query Processing", NLPRS 99, Beijing, China, November 5-7, 1999
• LIU Xiaohu, Pascale Fung, and CHEUNG Chi Shun, "A Monolingual Semantic Decoder Based on Word Sense Disambiguation for Mixed Language Understanding", EUROSPEECH 99, Budapest, Hungary: September 1999.
• Pascale Fung, LIU Xiaohu, and CHEUNG Chi Shun, "Mixed-language Query Disambiguation", ACL 99, Maryland: June 1999
• Pascale Fung, Cheung Chi Shun, Lam Kwok Leung, Lau Wai Kat, Lo Yuen Yee, "SALSA version 1.0, A Speech-Based Web Browser", ICSLP 98: Fifth International Conference on Spoken Language Processing, Sydney: Dec. 1998, vol.4, 1615-1619.
• MA Chi Yuen and Pascale Fung, "Using English Phoneme Models for Chinese Speech Recognition", International Symposium on Chinese Spoken language processing, HongKong: Dec. 1998, 80-82.
• Pascale Fung, CHEUNG Chi Shuen, LAM Kwok Leung, LIU Wai Kat, LO Yuen Yee, and MA Chi Yuen, "SALSA, A Multilingual Speech-Based Web Browser", The First AEARU Web Technolgy Workshop, Kyoto: Nov. 1998, 16-21.
• Pascale Fung and Lam Kwok Leung, "Are Initial/Final Units Acoustically Accurate?". In 1998 Workshop on Speech Processing, The Chinese University of Hong Kong, Hong Kong: Sep. 1998, 235--240
• Pascale Fung, Bertram Shi, Dekai Wu, Lam Wai Bun, Wong Shuen Kong, "Dealing with Multilinguality in a Spoken Language Query Translator", In ACL 97 Workshop on Spoken Language Translation, Madrid, Spain: Jul 1997, 40--43.
• Paul Placeway, Richard Schwartz, Pascale Fung, Long Nguyen, "The Estimation of Powerful Language Models from Small and Large Corpora", In ICASSP '93: International Conference on Acoustics, Signal and Speech Processing, San Francisco: Apr. 1993.
• M. Bates, R. Borrow, Pascale Fung, R. Ingria, F. Kubala, J.  Makhoul, L. Nguyen, R. Schwartz, D. Stallard, "The BBN/HARC Spoken Language Understanding System", In ICASSP '93: International Conference on Acoustics, Signal and Speech Processing, San Francisco: Apr. 1993.
• M. Bates, R. Borrow, Pascale Fung, R. Ingria, F. Kubala, J.  Makhoul, L. Nguyen, R. Schwartz, D. Stallard, "Design and Performance of HARC, the BBN Spoken Language Understanding System", In ICSLP '92: Second International Conference on Spoken Language Processing, Banff: Oct. 1992.

Robust Speech Recognition

• Shilei Huang, Xiang Xie and Pascale Fung, "Using Output Probability Distribution for OOV Word Rejection" in SLT 2008, 2008
• Ding, Pei, Bertram Shi, Pascale Fung, and Zhigang Cao, "Flooring the observation probability for robust ASR in impulsive noise compensation", in EUROSPEECH '03, Geneva, September 2003.
• K. S. Yao, B. E. Shi, Pascale Fung and Z. Cao, "Log-add approximation on-line noise compensation method adopting robust decision rules for robust digits recognition", Chinese Journal of Electronics, vol. 9, no. 3, pp.278-83, July 2000
• K. Yao, B. E. Shi, Pascale Fung and Z. Cao, "Residual noise compensation for robust speech recognition in nonstationary noise", IEEE Intl. Conf. On Acoustics, Speech and Signal Processing 2000, Istanbul, Turkey, vol. 2, pp. 1125-1128, June 2000.
• Liu, Yi and Pascale Fung, "Decision Tree-Based Triphones are Robust and Practical for Mandarin Speech Recognition", EUROSPEECH 99, Budapest, Hungary: September 1999.
• K. S. Yao, B. E. Shi, Pascale Fung and Z. Cao, "Liftered forward masking procedure for robust digits recognition", Proc. European Conf. on Speech Communication and Technology, Budapest, Hungary, vol. 6, pp. 2873-2876, Sep.  1999.
• LAM Kwok Leung and Pascale Fung, "A More Efficient and Optimal LLR for Decoding and Verification", In Proceedings of 1999 IEEE International Conference on   Acoustics, Speech, and Signal Processing, 1999. ICASSP '99, Volume: 2 , 15-19 March 1999   pp 689 - 692 vol.2.
• Pascale Fung, Tatsuya Kawahara, Martine Adda, Shuji Doshita, "Improved Speaker Markov Modeling for Unsupervised Speaker Normalization", In Studia Phonologica, XXV, 1991.
• Pascale Fung, Tatsuya Kawahara and Shuji Doshita, "Unsupervised Speaker Normalization by Speaker Markov Model Converter for Speaker-Independent Speech Recognition", In Eurospeech '91: Second European Conference on Speech Communication and Technology, Genoa: Sep. 1991, 1111--1114.