Top-Rank Enhanced Listwise Optimization for Statistical Machine Translation

by   Huadong Chen, et al.
Nanjing University
University of Notre Dame

Pairwise ranking methods are the basis of many widely used discriminative training approaches for structure prediction problems in natural language processing(NLP). Decomposing the problem of ranking hypotheses into pairwise comparisons enables simple and efficient solutions. However, neglecting the global ordering of the hypothesis list may hinder learning. We propose a listwise learning framework for structure prediction problems such as machine translation. Our framework directly models the entire translation list's ordering to learn parameters which may better fit the given listwise samples. Furthermore, we propose top-rank enhanced loss functions, which are more sensitive to ranking errors at higher positions. Experiments on a large-scale Chinese-English translation task show that both our listwise learning framework and top-rank enhanced listwise losses lead to significant improvements in translation quality.


page 1

page 2

page 3

page 4


MTIL17: English to Indian Langauge Statistical Machine Translation

English to Indian language machine translation poses the challenge of st...

Deep Attentive Ranking Networks for Learning to Order Sentences

We present an attention-based ranking framework for learning to order se...

A Batch Learning Framework for Scalable Personalized Ranking

In designing personalized ranking algorithms, it is desirable to encoura...

LSTM Neural Reordering Feature for Statistical Machine Translation

Artificial neural networks are powerful models, which have been widely a...

Learning to Stop in Structured Prediction for Neural Machine Translation

Beam search optimization resolves many issues in neural machine translat...

A simple discriminative training method for machine translation with large-scale features

Margin infused relaxed algorithms (MIRAs) dominate model tuning in stati...

L2R2: Leveraging Ranking for Abductive Reasoning

The abductive natural language inference task (αNLI) is proposed to eval...

Please sign up or login with your details

Forgot password? Click here to reset