On the Complementarity between Pre-Training and Back-Translation for Neural Machine Translation (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Experimental results show that PT and BT are nicely complementary to each other. |
| Approach: | They introduce two probing tasks for PT and BT respectively and investigate their complementarity. |
| Outcome: | The proposed methods establish state-of-the-art on the WMT16 English-Romanian and English-Russian benchmarks. |
Similar Papers
On the Complementarity between Pre-Training and Random-Initialization for Resource-Rich Machine Translation (2022.coling-1)
Copied to clipboard
| Challenge: | Pre-Training (PT) of text representations has been successfully applied to low-resource Neural Machine Translation (NMT) however, it often fails to achieve notable gains on resource-rich NMT on par with its Random-Initialization (RI) counterpart. |
| Approach: | They propose to combine pre-training and random-initialization techniques to achieve significant improvements in NMT. |
| Outcome: | The proposed model fusion algorithm can achieve significant improvements on two resource-rich translation benchmarks. |
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. |
Bridging the Gap between Training and Inference for Neural Machine Translation (P19-1)
Copied to clipboard
| Challenge: | Neural Machine Translation generates target words sequentially while at inference it has to generate the entire sequence from scratch. |
| Approach: | They propose to use ground truth and inference to generate target words sequentially while at inference it has to generate the entire sequence from scratch. |
| Outcome: | Experiments on Chinese->English and WMT’14 English->German translation tasks show that the proposed model can achieve significant improvements on multiple datasets. |
Synthetic Pre-Training Tasks for Neural Machine Translation (2023.findings-acl)
Copied to clipboard
| Challenge: | toxicity and bias can be addressed by pre-training with synthetic resources . BLEU scores are used to compare methods with real-world data . |
| Approach: | They propose several ways to generate obfuscated data from large parallel corpus and concatenating phrase pairs from small word-aligned corpus with synthetic parallel data without real human language corpora. |
| Outcome: | The proposed methods can be used to generate obfuscated data or synthetic parallel data without real human language corpora even with high levels of oblication. |
Tagged Back-translation Revisited: Why Does It Really Work? (2020.acl-main)
Copied to clipboard
| Challenge: | In this paper, we show that neural machine translation systems trained on large back-translated data overfit some of the characteristics of machine-transcribed texts. |
| Approach: | They propose to add a tag to back-translations to help distinguish back-translated data from original parallel training data. |
| Outcome: | The proposed tag helps the system distinguish back-translated data from original parallel training data and is as effective as a tag in high-resource training. |
When and Why Are Pre-Trained Word Embeddings Useful for Neural Machine Translation? (N18-2)
Copied to clipboard
| Challenge: | Pre-trained word embeddings have proven to be invaluable for improving performance in natural language analysis tasks where large-scale parallel corpora cannot be obtained. |
| Approach: | They perform five sets of experiments to analyze when pre-trained word embeddings can be useful in NMT tasks. |
| Outcome: | The embeddings provide gains of up to 20 BLEU points in the most favorable setting. |
Pivot-based Transfer Learning for Neural Machine Translation between Non-English Languages (D19-1)
Copied to clipboard
| Challenge: | Using parallel corpora, we train a single, direct NMT model for non-English language pairs. |
| Approach: | They propose three ways to increase the relation among source, pivot, and target languages in pre-training . they use additional adapter component to smoothly connect pre-trained encoder and decoder . |
| Outcome: | The proposed methods outperform multilingual models up to +2.6% BLEU in WMT 2019 French-German and German-Czech tasks. |
Language Modeling, Lexical Translation, Reordering: The Training Process of NMT through the Lens of Classical SMT (2021.emnlp-main)
Copied to clipboard
| Challenge: | Statistical MT decomposes the translation task into distinct components that are learned separately. |
| Approach: | They show that neural machine translation models acquire different competences over the course of training . previous work shows how to improve some of the competences in NMT by using lexical translation probabilities, phrase memories, alignment information. |
| Outcome: | The proposed model improves translation quality and word-by-word translation, while learning complex reordering patterns. |
On the Language Coverage Bias for Neural Machine Translation (2021.findings-acl)
Copied to clipboard
| Challenge: | Language coverage bias is important for neural machine translation because of the target-original training data. |
| Approach: | They propose two approaches to alleviate the language coverage bias problem by explicitly distinguishing between the source-and target-original training data. |
| Outcome: | The proposed methods improve translation tasks on both back-and forward-translation and their tagged variants. |
Evaluating Pre-training Objectives for Low-Resource Translation into Morphologically Rich Languages (2022.lrec-1)
Copied to clipboard
| Challenge: | a lack of parallel data is a major limitation for Neural Machine Translation systems, especially for morphologically rich languages. |
| Approach: | They propose to leverage target monolingual data to overcome the lack of parallel data . they introduce a new technique called PT-Inflect to train NMT systems . |
| Outcome: | The proposed techniques outperform NMT systems trained on parallel data on four typologically diverse target languages. |