Challenge: Neural machine translation suffers from exposure bias, and alternative approaches to mitigate this are under debate.
Approach: They propose to reduce exposure bias by using minimum risk training to mitigate hallucinations . they find that exposure bias is more problematic under domain shift .
Outcome: The proposed methods can reduce exposure bias even on in-domain test sets.

Similar Papers

Looking for a Needle in a Haystack: A Comprehensive Study of Hallucinations in Neural Machine Translation (2023.eacl-main)

Copied to clipboard

Challenge: Neural machine translation (NMT) is becoming more accurate, but hallucinations are extremely pathological . previous work focused on artificial settings where the problem is amplified, disregarding some common types of hallucines .
Approach: They propose a method for alleviating hallucinations at test time that significantly reduces the hallucinic rate.
Outcome: The proposed method significantly reduces the hallucinatory rate in a natural setting.
Understanding the Properties of Minimum Bayes Risk Decoding in Neural Machine Translation (2021.acl-long)

Copied to clipboard

Challenge: Neural Machine Translation (NMT) currently exhibits biases such as producing translations that are too short and overgenerating frequent words.
Approach: They propose to use minimum bayes risk decoding instead of beam search to investigate the effects of beam decoding on unbiased samples.
Outcome: The proposed method improves on a number of previously reported biases and failure cases of beam search on unbiased samples.
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.
Optimal Transport for Unsupervised Hallucination Detection in Neural Machine Translation (2023.acl-long)

Copied to clipboard

Challenge: Neural machine translation models can unpredictably produce severely pathological translations, known as hallucinations, that seriously undermine user trust.
Approach: They propose a fully unsupervised, plug-in detector that can be used with any attention-based NMT model.
Outcome: The proposed detector outperforms existing models and is competitive with detectors that employ external models trained on millions of samples.
Contrastive Decoding Reduces Hallucinations in Large Multilingual Machine Translation Models (2024.eacl-long)

Copied to clipboard

Challenge: Hallucinations occur when the target side sentence is detached from the source side sentence, or in other words, when there is a low contribution of the source sentence to the generation of the target sentence.
Approach: They propose to use Contrastive Decoding to maximise the log-likelihood difference between a model and the same model with reduced contribution from the encoder outputs.
Outcome: The proposed algorithm maximises the log-likelihood difference between a model and the same model with reduced contribution from the encoder outputs.
A Simple and Effective Approach to Coverage-Aware Neural Machine Translation (P18-2)

Copied to clipboard

Challenge: Neural Machine Translation (NMT) models are used to solve translation problems using long-term models.
Approach: They propose a method to seek a better balance between model confidence and length preference for Neural Machine Translation.
Outcome: The proposed model improves on Chinese-English and English-German translation tasks.
On Long-Tailed Phenomena in Neural Machine Translation (2020.findings-emnlp)

Copied to clipboard

Challenge: State-of-the-art Neural Machine Translation models struggle with generating low-frequency tokens, tackling which remains a major challenge.
Approach: They propose a loss function to better adapt model training to structural dependencies of conditional text generation by incorporating inductive biases of beam search into the training process.
Outcome: The proposed method leads to significant gains over cross-entropy across different language pairs, especially on the generation of low-frequency words.
The Curious Case of Hallucinations in Neural Machine Translation (2021.naacl-main)

Copied to clipboard

Challenge: Neural Machine Translation (NMT) suffers from well known pathologies such as coverage, mistranslation of named entities, etc.
Approach: They propose a theory that explains hallucinations under source perturbation and a method that generates hallucines under corpus-level noise without any source perturbations.
Outcome: The proposed hypothesis is validated by a corpus-level noise analysis and is validateable in other datasets.
Specializing Multi-domain NMT via Penalizing Low Mutual Information (2022.emnlp-main)

Copied to clipboard

Challenge: Multi-domain Neural Machine Translation (NMT) trains a single model with multiple domains.
Approach: They propose a method that penalizes low MI to be higher for domain-specific NMTs.
Outcome: The proposed method achieves state-of-the-art performance among current models . it also promotes low MI to be higher resulting in domain-specialized multi-domain NMT.
Multi-Domain Neural Machine Translation with Word-Level Domain Context Discrimination (D18-1)

Copied to clipboard

Challenge: Experimental results on Chinese-English and English-French multi-domain translation tasks demonstrate the effectiveness of the proposed model.
Approach: They propose to use mixed-domain parallel sentences to construct a unified model that allows translation to switch between different domains.
Outcome: The proposed model distinguishes and exploits word-level domain contexts on Chinese-English and English-French translation tasks.

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