An Efficient, Probabilistically Sound Algorithm for Segmentation andWord Discovery
Machine Learning - Special issue on natural language learning
Approximation algorithms for grammar-based compression
SODA '02 Proceedings of the thirteenth annual ACM-SIAM symposium on Discrete algorithms
A statistical model for word discovery in transcribed speech
Computational Linguistics
Linguistic structure as composition and perturbation
ACL '96 Proceedings of the 34th annual meeting on Association for Computational Linguistics
Unsupervised discovery of morphemes
MPL '02 Proceedings of the ACL-02 workshop on Morphological and phonological learning - Volume 6
Grammar induction by MDL-based distributional classification
New developments in parsing technology
An algorithm for unsupervised topic discovery from broadcast news stories
HLT '02 Proceedings of the second international conference on Human Language Technology Research
Voting experts: An unsupervised algorithm for segmenting sequences
Intelligent Data Analysis
Applications of corpus-based semantic similarity and word segmentation to database schema matching
The VLDB Journal — The International Journal on Very Large Data Bases
CICLing '07 Proceedings of the 8th International Conference on Computational Linguistics and Intelligent Text Processing
Morphemes as necessary concept for structures discovery from untagged corpora
NeMLaP3/CoNLL '98 Proceedings of the Joint Conferences on New Methods in Language Processing and Computational Natural Language Learning
Hi-index | 0.00 |
We present an unsupervised learning algorithm that acquires a natural- language lexicon from raw speech. The algorithm is based on the optimal encoding of symbol sequences in an MDL framework, and uses a hierarchical representation of language that overcomes many of the problems that have stymied previous grammar-induction procedures. The forward mapping from symbol sequences to the speech stream is modeled using features based on articulatory gestures. We present results on the acquisition of lexicons and language models from raw speech, text, and phonetic transcripts, and demonstrate that our algorithm compares very favorably to other reported results with respect to segmentation performance and statistical efficiency.