paper-with-me

홈 › Papers

Semi-Autoregressive Training Improves Mask-Predict Decoding

2020-01-23 · Marjan Ghazvininejad, Omer Levy, Luke Zettlemoyer

The recently proposed mask-predict decoding algorithm has narrowed the performance gap between semi-autoregressive machine translation models and the traditional left-to-right approach. We introduce a new training method for conditional masked language models, SMART, which mimics the semi-autoregressive behavior of mask-predict, producing training examples that contain model predictions as part of their inputs. Models trained with SMART produce higher-quality translations when using mask-predict decoding, effectively closing the remaining performance gap with fully autoregressive models.

📄 PDF Abstract BibTeX arXiv:2001.08785

Code (0)

등록된 구현이 없습니다.

Tasks

Machine TranslationTranslation

Similar Papers 제목 키워드 기반

Inference Strategies for Machine Translation with Conditional Masking

2020-10-05 · EMNLP 2020 11 · Julia Kreutzer, George Foster, Colin Cherry

Conditional masked language model (CMLM) training has proven successful for non-autoregressive and semi-autoregressive sequence generation tasks, such as machine translation. Given a trained CMLM, however, it is not clea…

Language ModelingLanguage ModellingMachine TranslationTranslation

Simple and Effective Masked Diffusion Language Models

2024-06-11 · Subham Sekhar Sahoo, Marianne Arriola, Yair Schiff, Aaron Gokaslan 외

While diffusion models excel at generating high-quality images, prior work reports a significant performance gap between diffusion and autoregressive (AR) methods in language modeling. In this work, we show that simple m…

Language ModelingLanguage ModellingMasked Language Modeling

LESS Is More: Mutual-Stability Sampling for Diffusion Language Models

2026-06-15 · Amr Mohamed, Guokan Shang, Michalis Vazirgiannis arxiv

Diffusion large language models (dLLMs) offer a promising alternative to autoregressive decoding by iteratively refining masked sequences, enabling parallel token updates and bidirectional conditioning. Their practical e…

General Knowledge

HAINAN: Fast and Accurate Transducer for Hybrid-Autoregressive ASR

2024-10-03 · Hainan Xu, Travis M. Bartley, Vladimir Bataev, Boris Ginsburg

We present Hybrid-Autoregressive INference TrANsducers (HAINAN), a novel architecture for speech recognition that extends the Token-and-Duration Transducer (TDT) model. Trained with randomly masked predictor network outp…

speech-recognitionSpeech Recognition

Mask-Predict: Parallel Decoding of Conditional Masked Language Models

2019-04-19 · IJCNLP 2019 11 · Marjan Ghazvininejad, Omer Levy, Yinhan Liu, Luke Zettlemoyer

Most machine translation systems generate text autoregressively from left to right. We, instead, use a masked language modeling objective to train a model to predict any subset of the target words, conditioned on both th…

Language ModelingLanguage ModellingMachine TranslationMasked Language Modeling+1