Mutual Information and Diverse Decoding Improve Neural Machine Translation
Explore this paper's citation graph
Summary
This work introduces an alternative objective function for neural MT that maximizes the mutual information between the source and target sentences, modeling the bi-directional dependency of sources and targets.
- Type
- preprint
- Published
- 2016-01-04
- Cited by
- 129
- References
- 39
- Access
- Open access
- OpenAlex
- https://openalex.org/W2222235228
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:308306
Keywords
Decoding methods, Machine translation, Computer science, Translation (biology), Neural decoding
References
- Trait-Based Hypothesis Selection For Machine Translation
- Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models
- Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
- A Neural Network Approach to Context-Sensitive Generation of Conversational Responses
- A Neural Conversational Model
- Recurrent Continuous Translation Models
- Neural Machine Translation of Rare Words with Subword Units
- Maximum mutual information estimation of hidden Markov model parameters for speech recognition
- Effective Approaches to Attention-based Neural Machine Translation
- On Using Monolingual Corpora in Neural Machine Translation
- Bagging and Boosting statistical machine translation systems
- Large scale discriminative training of hidden Markov models for speech recognition
- String-to-Dependency Statistical Machine Translation
- Long Short-Term Memory
- Solving the Problem of Cascading Errors: Approximate Bayesian Inference for Linguistic Annotation Pipelines
- Lattice Minimum Bayes-Risk Decoding for Statistical Machine Translation
- On Using Very Large Target Vocabulary for Neural Machine Translation
- Bleu: a Method for Automatic Evaluation of Machine Translation
- Lattice-based Minimum Error Rate Training for Statistical Machine Translation
- A Hierarchical Neural Autoencoder for Paragraphs and Documents
Cited by
- Noisy Parallel Approximate Decoding for Conditional Recurrent Language Model
- Review of state-of-the-arts in artificial intelligence with application to AI safety problem
- MetaMind Neural Machine Translation System for WMT 2016
- Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Models
- Neural Machine Translation by Minimising the Bayes-risk with Respect to Syntactic Translation Lattices
- Decoding as Continuous Optimization in Neural Machine Translation
- Grammatical error correction in non-native English
- Making 360° Video Watchable in 2D: Learning Videography for Click Free Viewing
- Natural Language Generation for Spoken Dialogue System using RNN Encoder-Decoder Networks
- Data Augmentation with Seq2Seq Models
- Single-Queue Decoding for Neural Machine Translation
- Towards Decoding as Continuous Optimisation in Neural Machine Translation
- Maximum Expected Likelihood Estimation for Zero-resource Neural Machine Translation
- Detecting Untranslated Content for Neural Machine Translation
- Neural Machine Translation
- Towards domain adaptation for Neural Network Language Generation in Dialogue
- Diversifying Neural Conversation Model with Maximal Marginal Relevance
- Neural Machine Translation
- Towards a Neural Conversation Model With Diversity Net Using Determinantal Point Processes
- Diverse Beam Search for Improved Description of Complex Scenes
Related papers
- Recurrent Stacking of Layers for Compact Neural Machine Translation Models
- Model-based neural decoding of reaching movements: a maximum likelihood approach
- Comparing decoding performance between functionally defined neural populations
- Trainable Greedy Decoding for Neural Machine Translation
- Neural Decoding for Location of Macaque’s Moving Finger Using Generative Adversarial Networks
- Stacked recurrent neural network for decoding of reaching movement using local field potentials and single-unit spikes
- Improving the accuracy of decoding monkey brain-machine interface data by estimating the state of unobserved cell assemblies.
- Firing rate estimation using infinite mixture models and its application to neural decoding.