A Cache-Based Natural Language Model for Speech Recognition
IEEE Transactions on Pattern Analysis and Machine Intelligence
A dynamic language model for speech recognition
HLT '91 Proceedings of the workshop on Speech and Natural Language
Elements of information theory
Elements of information theory
A maximum entropy approach to natural language processing
Computational Linguistics
Inducing Features of Random Fields
IEEE Transactions on Pattern Analysis and Machine Intelligence
Modelling Word-Pair Relations in a Category-Based Language Model
ICASSP '97 Proceedings of the 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP '97)-Volume 2 - Volume 2
Theory, Volume 1, Queueing Systems
Theory, Volume 1, Queueing Systems
Statistical Models for Text Segmentation
Machine Learning - Special issue on natural language learning
Word document density and relevance scoring (poster session)
SIGIR '00 Proceedings of the 23rd annual international ACM SIGIR conference on Research and development in information retrieval
Using micro information units for internet search
Proceedings of the eleventh international conference on Information and knowledge management
Eliminating noisy information in Web pages for data mining
Proceedings of the ninth ACM SIGKDD international conference on Knowledge discovery and data mining
Advances in domain independent linear text segmentation
NAACL 2000 Proceedings of the 1st North American chapter of the Association for Computational Linguistics conference
Trigger-pair predictors in parsing and tagging
COLING '98 Proceedings of the 17th international conference on Computational linguistics - Volume 1
A Dynamic Programming Algorithm for Linear Text Segmentation
Journal of Intelligent Information Systems
A very very large corpus doesn't always yield reliable estimates
COLING-02 proceedings of the 6th conference on Natural language learning - Volume 20
On document relevance and lexical cohesion between query terms
Information Processing and Management: an International Journal
Fast computation of lexical affinity models
COLING '04 Proceedings of the 20th international conference on Computational Linguistics
A proximity language model for information retrieval
Proceedings of the 32nd international ACM SIGIR conference on Research and development in information retrieval
Web page cleaning for web mining through feature weighting
IJCAI'03 Proceedings of the 18th international joint conference on Artificial intelligence
Legal document clustering with built-in topic segmentation
Proceedings of the 20th ACM international conference on Information and knowledge management
Spectral composition of semantic spaces
QI'11 Proceedings of the 5th international conference on Quantum interaction
Leximancer concept mapping of patient case studies
KES'05 Proceedings of the 9th international conference on Knowledge-Based Intelligent Information and Engineering Systems - Volume Part III
Basic word completion and prediction for hebrew
SPIRE'12 Proceedings of the 19th international conference on String Processing and Information Retrieval
Connecting the dots: mass, energy, word meaning, and particle-wave duality
QI'12 Proceedings of the 6th international conference on Quantum Interaction
Hi-index | 0.00 |
This paper introduces new methods based on exponential families for modeling the correlations between words in text and speech. While previous work assumed the effects of word co-occurrence statistics to be constant over a window of several hundred words, we show that their influence is nonstationary on a much smaller time scale. Empirical data drawn from English and Japanese text, as well as conversational speech, reveals that the "attraction" between words decays exponentially, while stylistic and syntactic contraints create a "repulsion" between words that discourages close co-occurrence. We show that these characteristics are well described by simple mixture models based on two-stage exponential distributions which can be trained using the EM algorithm. The resulting distance distributions can then be incorporated as penalizing features in an exponential language model.