Search Engine Guided Non-Parametric Neural Machine Translation

Abstract

In this paper, we extend an attention-based neural machine translation (NMT) model by allowing it to access an entire training set of parallel sentence pairs even after training. The proposed approach consists of two stages. In the first stage--retrieval stage--, an off-the-shelf, black-box search engine is used to retrieve a small subset of sentence pairs from a training set given a source sentence. These pairs are further filtered based on a fuzzy matching score based on edit distance. In the second stage--translation stage--, a novel translation model, called translation memory enhanced NMT (TM-NMT), seamlessly uses both the source sentence and a set of retrieved sentence pairs to perform the translation. Empirical evaluation on three language pairs (En-Fr, En-De, and En-Es) shows that the proposed approach significantly outperforms the baseline approach and the improvement is more significant when more relevant sentence pairs were retrieved.

Accepted by AAAI 2018

References in corpus (13)

• Sequence to Sequence Learning with Neural Networks
• Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
• Large-scale Simple Question Answering with Memory Networks
• On Using Monolingual Corpora in Neural Machine Translation
• Learning to Remember Rare Events
• Exploring Nearest Neighbor Approaches for Image Captioning
• Does Neural Machine Translation Benefit from Larger Context?
• SYSTRAN's Pure Neural Machine Translation Systems
• Dynamic Neural Turing Machine with Soft and Hard Addressing Schemes
• Exploiting Cross-Sentence Context for Neural Machine Translation
• Task-Oriented Query Reformulation with Reinforcement Learning
• Learning to Parse and Translate Improves Neural Machine Translation
• Predicting Target Language CCG Supertags Improves Neural Machine Translation

Cited by in corpus (11)

• Generating Sentences by Editing Prototypes
• Fast Parametric Learning with Activation Memorization
• Guiding Neural Machine Translation with Retrieved Translation Pieces
• Retrieve and Refine: Improved Sequence Generation Models For Dialogue
• Improving Multi-turn Dialogue Modelling with Utterance ReWriter
• Neural Machine Translation with Noisy Lexical Constraints
• Controlling Decoding for More Abstractive Summaries with Copy-Based Networks
• Coupling Retrieval and Meta-Learning for Context-Dependent Semantic Parsing
• Retrieval-Augmented Convolutional Neural Networks for Improved Robustness against Adversarial Examples
• Neural Machine Translation with Key-Value Memory-Augmented Attention
• Contextual Memory Trees