On the Information Redundancy in Non-Autoregressive Translation
Token repetition is a typical form of multi-modal problem in fully non-autoregressive translation (NAT). In this work, we revisit the multi-modal problem in recently proposed NAT models. Our study reveals that these advanced models have introduced other types of information redundancy errors, which cannot be measured by the conventional metric - the continuous repetition ratio. By manually annotating the NAT outputs, we identify two types of information redundancy errors that correspond well to lexical and reordering multi-modality problems. Since human annotation is time-consuming and labor-intensive, we propose automatic metrics to evaluate the two types of redundant errors. Our metrics allow future studies to evaluate new methods and gain a more comprehensive understanding of their effectiveness.
Code (0)
등록된 구현이 없습니다.
Tasks
TranslationSimilar Papers 제목 키워드 기반
Transformer-Encoder Trees for Efficient Multilingual Machine Translation and Speech Translation
Multilingual translation suffers from computational redundancy, especially when translating into multiple languages simultaneously. In addition, translation quality can suffer for low-resource languages. To address this,…
Machine TranslationSpeech RecognitionImproving Autoregressive NMT with Non-Autoregressive Model
Autoregressive neural machine translation (NMT) models are often used to teach non-autoregressive models via knowledge distillation. However, there are few studies on improving the quality of autoregressive translation (…
Decoderde-enKnowledge DistillationMachine Translation+3Guiding Non-Autoregressive Neural Machine Translation Decoding with Reordering Information
Non-autoregressive neural machine translation (NAT) generates each target word in parallel and has achieved promising inference acceleration. However, existing NAT models still have a big gap in translation quality compa…
Machine TranslationTranslationRetrieving Sequential Information for Non-Autoregressive Neural Machine Translation
Non-Autoregressive Transformer (NAT) aims to accelerate the Transformer model through discarding the autoregressive mechanism and generating target words independently, which fails to exploit the target sequential inform…
DecoderMachine TranslationSentenceTranslationSkipVAR: Accelerating Visual Autoregressive Modeling via Adaptive Frequency-Aware Skipping
Recent studies on Visual Autoregressive (VAR) models have highlighted that high-frequency components, or later steps, in the generation process contribute disproportionately to inference latency. However, the underlying …
Image GenerationSSIM