On the use of BERT for Neural Machine Translation (D19-56)

Copied to clipboard

Challenge: Existing studies on using pretrained language models for supervised NMT have not been successful.
Approach: They propose to integrate BERT pretrained models with supervised NMT models by using monolingual data.
Outcome: The proposed models improve translation quality in English-German, English-Russian and IWSLT14 datasets.

Similar Papers

BERTology for Machine Translation: What BERT Knows about Linguistic Difficulties for Translation (2022.lrec-1)

Copied to clipboard

Challenge: Pre-trained transformer-based models have shown excellent performance in most benchmark tests, but lack a good understanding of the linguistic knowledge of BERT in Neural Machine Translation (NMT).
Approach: They propose to use QE models to analyze BERT's syntactic dependencies and their impact on machine translation quality.
Outcome: The proposed model is able to model with self-attention in the pre-training phase, which improves generalization ability.
A Comparison between Pre-training and Large-scale Back-translation for Neural Machine Translation (2021.findings-acl)

Copied to clipboard

Challenge: BERT is a promising technique to improve NMT, but how it outperforms standard NMT is understudied.
Approach: We compare MT engines trained with pre-trained BERT and back-translation with incrementally larger amounts of data.
Outcome: The proposed technique outperforms standard NMT models on morphology and syntax.
BERT, mBERT, or BiBERT? A Study on Contextualized Embeddings for Neural Machine Translation (2021.emnlp-main)

Copied to clipboard

Challenge: Existing methods for incorporating pre-trained models into NMT systems are non-trivial and lack a comparison of the impact that other pre-trainers may have on translation performance.
Approach: They propose to use the input of a bilingual pre-trained language model as the input for NMT encoders and a stochastic layer selection approach to ensure sufficient utilization of contextualized embeddings.
Outcome: The proposed bilingual pre-trained language model outperforms all other pre-train models on the IWSLT’14 dataset and the proposed dual-directional translation model.
Recycling a Pre-trained BERT Encoder for Neural Machine Translation (D19-56)

Copied to clipboard

Challenge: In monolingual tasks, the number of unlearned model parameters is as huge as the number learned parameters in the BERT model.
Approach: They propose to apply a pre-trained Bidirectional Encoder Representations from Transformers (BERT) model to Transformer-based neural machine translation (NMT) based on the Transformer.
Outcome: The proposed model is stable and efficient in low-resource settings.
On the differences between BERT and MT encoder spaces and how to address them in translation tasks (2021.acl-srw)

Copied to clipboard

Challenge: Various studies show that pretrained language models cannot replace encoders in neural machine translation despite their success in other tasks.
Approach: They propose a supervised transformation from one into the other to improve the applicability of BERT in neural machine translation.
Outcome: The proposed transformations show that they cannot replace encoders in MT despite their success in other tasks.
Better Neural Machine Translation by Extracting Linguistic Information from BERT (2021.eacl-main)

Copied to clipboard

Challenge: Experimental results show that incorporating linguistic information into neural machine translation models is no more difficult to train than conventional Transformer-based NMT.
Approach: They propose to extract linguistic information from contextual word embeddings instead of point estimates to augment NMT models.
Outcome: The proposed method generalizes better in a variety of training contexts and is no more difficult to train than conventional Transformer-based NMT.
Can Monolingual Pretrained Models Help Cross-Lingual Classification? (2020.aacl-main)

Copied to clipboard

Challenge: Multilingual pretrained language models have shown impressive results for cross-lingual transfer, but due to the constant model capacity, multilingual pre-training usually lags behind the monolingual competitors.
Approach: They propose to transfer the knowledge from monolingual pretrained models to multilingual ones to improve zero-shot cross-lingual classification by using machine translation systems.
Outcome: The proposed methods outperform vanilla multilingual fine-tuning on two cross-lingual classification benchmarks.
BERTGen: Multi-task Generation through BERT (2021.acl-long)

Copied to clipboard

Challenge: Recent work in unsupervised and self-supervised pre-training has revolutionised the field of natural language understanding (NLU).
Approach: They propose to use multimodal and multilingual pre-trained models to extend BERT by fusing them together for language generation tasks.
Outcome: The proposed model outperforms baseline models in image captioning, machine translation and multimodal machine translation tasks and is competitive with supervised counterparts.
Pre-training Methods for Neural Machine Translation (2021.acl-tutorials)

Copied to clipboard

Challenge: This tutorial provides a comprehensive guide to make the most of pre-training for neural machine translation.
Approach: This tutorial provides a comprehensive guide to make the most of pre-training for neural machine translation.
Outcome: This tutorial explains how to make the most of pre-training for neural machine translation.
Document-Level Neural Machine Translation Using BERT as Context Encoder (2020.aacl-srw)

Copied to clipboard

Challenge: Large-scale pre-trained representations such as BERT have been widely used in many natural language understanding tasks.
Approach: They propose to use BERT as a context encoder to achieve document-level contextual information, which is then integrated into both the encoder and decoder.
Outcome: The proposed model outperforms strong document-level machine translation baselines on BLEU score and captures document- level context information to boost translation performance.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations