Hallucinations in neural machine translation
Neural machine translation (NMT) systems have reached state of the art performance in translating text and widely deployed. Yet little is understood about how these systems function or break. Here we show that NMT systems are susceptible to producing highly pathological translations that are completely untethered from the source material, which we term hallucinations. Such pathological translations are problematic because they are are deeply disturbing of user trust and easy to find. We describe a method t generate hallucinations and show that many common variations of the NMT architecture are susceptible to them. We study a variety of approaches to reduce the frequency of hallucinations, including data augmentation, dynamical systems and regularization techniques and show that data augmentation significantly reduces hallucination frequency. Finally, we analyze networks that produce hallucinations and show signatures of hallucinations in the attention matrix and in the stability measures of the decoder.
Code (0)
등록된 구현이 없습니다.
Tasks
Data AugmentationDecoderHallucinationMachine TranslationNMTTranslationSimilar Papers 제목 키워드 기반
The Curious Case of Hallucinations in Neural Machine Translation
In this work, we study hallucinations in Neural Machine Translation (NMT), which lie at an extreme end on the spectrum of NMT pathologies. Firstly, we connect the phenomenon of hallucinations under source perturbation to…
HallucinationKnowledge DistillationMachine TranslationNMT+1Hallucinations in Large Multilingual Translation Models
Large-scale multilingual machine translation systems have demonstrated remarkable ability to translate directly between numerous languages, making them increasingly appealing for real-world applications. However, when de…
Language ModelingLanguage ModellingLarge Language ModelMachine Translation+1Hallucinations in Neural Machine Translation
Neural machine translation (NMT) systems have reached state of the art performance in translating text and are in wide deployment. Yet little is understood about how these systems function or break. Here we show that N…
Data AugmentationDecoderHallucinationMachine Translation+2Reducing Hallucinations in Neural Machine Translation with Feature Attribution
Neural conditional language generation models achieve the state-of-the-art in Neural Machine Translation (NMT) but are highly dependent on the quality of parallel training dataset. When trained on low-quality datasets, t…
Machine TranslationNMTText GenerationTranslationDetecting and Mitigating Hallucinations in Machine Translation: Model Internal Workings Alone Do Well, Sentence Similarity Even Better
While the problem of hallucinations in neural machine translation has long been recognized, so far the progress on its alleviation is very little. Indeed, recently it turned out that without artificially encouraging mode…
Machine TranslationSentenceSentence SimilarityTranslation