paper-with-me

Papers

Transformer-based Double-token Bidirectional Autoregressive Decoding in Neural Machine Translation

2020-12-01 · AACL (WAT) 2020 12 · Kenji Imamura, Eiichiro Sumita

This paper presents a simple method that extends a standard Transformer-based autoregressive decoder, to speed up decoding. The proposed method generates a token from the head and tail of a sentence (two tokens in total) in each step. By simultaneously generating multiple tokens that rarely depend on each other, the decoding speed is increased while the degradation in translation quality is minimized. In our experiments, the proposed method increased the translation speed by around 113%-155% in comparison with a standard autoregressive decoder, while degrading the BLEU scores by no more than 1.03. It was faster than an iterative non-autoregressive decoder in many conditions.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

DecoderMachine TranslationSentenceTranslation

Similar Papers 제목 키워드 기반

Towards End-to-End Generative Modeling of Long Videos with Memory-Efficient Bidirectional Transformers

2023-03-20 · CVPR 2023 1 · Jaehoon Yoo, Semin Kim, Doyup Lee, Chiheon Kim 외

Autoregressive transformers have shown remarkable success in video generation. However, the transformers are prohibited from directly learning the long-term dependency in videos due to the quadratic complexity of self-at…

Video Generation

Non-autoregressive Transformer with Unified Bidirectional Decoder for Automatic Speech Recognition

2021-09-14 · Chuan-Fei Zhang, Yan Liu, Tian-Hao Zhang, Song-Lu Chen 외

Non-autoregressive (NAR) transformer models have been studied intensively in automatic speech recognition (ASR), and a substantial part of NAR transformer models is to use the casual mask to limit token dependencies. How…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Decoderspeech-recognition+1

Fast Interleaved Bidirectional Sequence Generation

2020-10-27 · WMT (EMNLP) 2020 11 · Biao Zhang, Ivan Titov, Rico Sennrich

Independence assumptions during sequence generation can speed up inference, but parallel generation of highly inter-dependent tokens comes at a cost in quality. Instead of assuming independence between neighbouring token…

DecoderDocument SummarizationMachine Translation

Sequence Generation: From Both Sides to the Middle

2019-06-23 · Long Zhou, Jiajun Zhang, Cheng-qing Zong, Heng Yu

The encoder-decoder framework has achieved promising process for many sequence generation tasks, such as neural machine translation and text summarization. Such a framework usually generates a sequence token by token fro…

DecoderMachine TranslationSentenceText Summarization+1

UNCAGE: Contrastive Attention Guidance for Masked Generative Transformers in Text-to-Image Generation

2025-08-07 · Wonjun Kang, Byeongkeun Ahn, Minjae Lee, Kevin Galim 외 arxiv

Text-to-image (T2I) generation has been actively studied using Diffusion Models and Autoregressive Models. Recently, Masked Generative Transformers have gained attention as an alternative to Autoregressive Models to over…

Text-to-Image Generation