BERT, mBERT, or BiBERT? A Study on Contextualized Embeddings for Neural Machine Translation

EMNLP 2021  ·  Haoran Xu, Benjamin Van Durme, Kenton Murray ·

The success of bidirectional encoders using masked language models, such as BERT, on numerous natural language processing tasks has prompted researchers to attempt to incorporate these pre-trained models into neural machine translation (NMT) systems. However, proposed methods for incorporating pre-trained models are non-trivial and mainly focus on BERT, which lacks a comparison of the impact that other pre-trained models may have on translation performance. In this paper, we demonstrate that simply using the output (contextualized embeddings) of a tailored and suitable bilingual pre-trained language model (dubbed BiBERT) as the input of the NMT encoder achieves state-of-the-art translation performance. Moreover, we also propose a stochastic layer selection approach and a concept of dual-directional translation model to ensure the sufficient utilization of contextualized embeddings. In the case of without using back translation, our best models achieve BLEU scores of 30.45 for En->De and 38.61 for De->En on the IWSLT'14 dataset, and 31.26 for En->De and 34.94 for De->En on the WMT'14 dataset, which exceeds all published numbers.

PDF Abstract EMNLP 2021 PDF EMNLP 2021 Abstract

Datasets


Results from the Paper


 Ranked #1 on Machine Translation on IWSLT2014 German-English (using extra training data)

     Get a GitHub badge
Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data
Result Benchmark
Machine Translation IWSLT2014 German-English BiBERT BLEU score 38.61 # 1
Machine Translation WMT2014 English-German BiBERT BLEU score 31.26 # 5
Machine Translation WMT2014 German-English BiBERT BLEU score 34.94 # 2

Methods