DeepAI AI Chat
Log In Sign Up

A Simple Baseline for Beam Search Reranking

by   Lior Vassertail, et al.

Reranking methods in machine translation aim to close the gap between common evaluation metrics (e.g. BLEU) and maximum likelihood learning and decoding algorithms. Prior works address this challenge by training models to rerank beam search candidates according to their predicted BLEU scores, building upon large models pretrained on massive monolingual corpora – a privilege that was never made available to the baseline translation model. In this work, we examine a simple approach for training rerankers to predict translation candidates' BLEU scores without introducing additional data or parameters. Our approach can be used as a clean baseline, decoupled from external factors, for future research in this area.


page 1

page 2

page 3

page 4


A Streaming Approach For Efficient Batched Beam Search

We propose an efficient batching strategy for variable-length decoding o...

Machine Translation Decoding beyond Beam Search

Beam search is the go-to method for decoding auto-regressive machine tra...

Rethinking the Evaluation of Neural Machine Translation

The evaluation of neural machine translation systems is usually built up...

ParaCotta: Synthetic Multilingual Paraphrase Corpora from the Most Diverse Translation Sample Pair

We release our synthetic parallel paraphrase corpus across 17 languages:...

Facebook AI's WAT19 Myanmar-English Translation Task Submission

This paper describes Facebook AI's submission to the WAT 2019 Myanmar-En...

A Stable and Effective Learning Strategy for Trainable Greedy Decoding

As a widely used approximate search strategy for neural network decoders...

Speed-Constrained Tuning for Statistical Machine Translation Using Bayesian Optimization

We address the problem of automatically finding the parameters of a stat...