Alignment by agreement
2006
433 citations
Abstract
We present an unsupervised approach to symmetric word alignment in which two simple asymmetric models are trained jointly to maximize a combination of data likelihood and agreement between the models. Compared to the standard practice of intersecting predictions of independently-trained models, joint training provides a 32% reduction in AER. Moreover, a simple and efficient pair of HMM aligners provides a 29% reduction in AER over symmetrized IBM model 4 predictions.
Keywords
Simple (philosophy)IBMComputer scienceAgreementReduction (mathematics)Hidden Markov modelWord (group theory)Artificial intelligencePattern recognition (psychology)AlgorithmMathematics
Affiliated Institutions
Related Publications
Lattice-based optimization of sequence classification criteria for neural-network acoustic modeling
Acoustic models used in hidden Markov model/neural-network (HMM/NN) speech recognition systems are usually trained with a frame-based cross-entropy error criterion. In contrast,...
Feature-rich part-of-speech tagging with a cyclic dependency network
We present a new part-of-speech tagger that demonstrates the following ideas: (i) explicit use of both preceding and following tag contexts via a dependency network representati...
Sparse Multilayer Perceptron for Phoneme Recognition
This paper introduces the sparse multilayer perceptron (SMLP) which jointly learns a sparse feature representation and nonlinear classifier boundaries to optimally discriminate ...
Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups
Most current speech recognition systems use hidden Markov models (HMMs) to deal with the temporal variability of speech and Gaussian mixture models (GMMs) to determine how well ...
Deep Belief Networks using discriminative features for phone recognition
Deep Belief Networks (DBNs) are multi-layer generative models. They can be trained to model windows of coefficients extracted from speech and they discover multiple layers of fe...
Publication Info
- Year
- 2006
- Type
- article
- Pages
- 104-111
- Citations
- 433
- Access
- Closed
External Links
Social Impact
Altmetric
PlumX Metrics
Social media, news, blog, policy document mentions
Citation Metrics
433
OpenAlex
Cite This
Percy Liang,
Ben Taskar,
Dan Klein
(2006).
Alignment by agreement.
, 104-111.
https://doi.org/10.3115/1220835.1220849
Identifiers
- DOI
- 10.3115/1220835.1220849