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. |
Similar Papers
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. |
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. |
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. |
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 Simple and Effective Unified Encoder for Document-Level Machine Translation (2020.acl-main)
Copied to clipboard
| Challenge: | Existing models for document-level machine translation use two separate encoders to model the source sentences and document- level contexts. |
| Approach: | They propose a unified encoder that can outperform existing models of dual-encoder models . they propose to use document-level contexts to model the interaction between the contexts and the source sentences . |
| Outcome: | The proposed model outperforms baseline models of dual-encoder models in terms of BLEU and METEOR scores. |
A Primer in BERTology: What We Know About How BERT Works (2020.tacl-1)
Copied to clipboard
| Challenge: | a new study examines the current state of knowledge about the BERT model . the model is a stack of transformer encoder layers that are based on multiple self-attention ''heads'' |
| Approach: | They present a survey of over 150 studies of the popular Transformer-based model BERT . they discuss the current state of knowledge about how BERT works and how it is represented . |
| Outcome: | The proposed model is based on the Transformer-based model with state-of-the-art results . the proposed model has little cognitive motivation and is too small to perform ablation studies . |
How Multilingual is Multilingual BERT? (P19-1)
Copied to clipboard
| Challenge: | Existing studies have shown that deep, contextualized language models can encode syntactic and named entity information, but they have focused on what models trained on English capture about English. |
| Approach: | They propose a multilingual model pre-trained from monolingual Wikipedia corpora . they show that multilingual BERT is surprisingly good at zero-shot cross-lingual model transfer . |
| Outcome: | The proposed model can find translation pairs, but it exhibits systematic deficiencies affecting certain language pairs. |
E-BERT: Efficient-Yet-Effective Entity Embeddings for BERT (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods to enhance BERT with factual knowledge about entities require no additional pretraining and no changes to the encoder itself. |
| Approach: | They propose a way to inject factual knowledge into the pretrained BERT model by aligning Wikipedia2Vec entity vectors with BERT's native wordpiece vector space and feeding the aligned entity vector into BERT as if they were wordpieces. |
| Outcome: | The proposed version outperforms baseline models on unsupervised question answering, supervised relation classification and entity linking tasks. |
Contextual Embeddings: When Are They Worth It? (2020.acl-main)
Copied to clipboard
| Challenge: | In recent years, rich contextual embeddings have enabled rapid progress on benchmarks like GLUE, but require significant computational resources during pretraining and during downstream task training and inference. |
| Approach: | They empirically compare contextual embeddings with classic pretrained embedders and a random word embeddable with a simple baseline. |
| Outcome: | The proposed models perform within 5 to 10% accuracy on industry-scale data. |
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. |