paper-with-me

홈 › Papers

Integrated Training for Sequence-to-Sequence Models Using Non-Autoregressive Transformer

2021-09-27 · ACL (IWSLT) 2021 8 · Evgeniia Tokarchuk, Jan Rosendahl, Weiyue Wang, Pavel Petrushkov, Tomer Lancewicki, Shahram Khadivi, Hermann Ney

Complex natural language applications such as speech translation or pivot translation traditionally rely on cascaded models. However, cascaded models are known to be prone to error propagation and model discrepancy problems. Furthermore, there is no possibility of using end-to-end training data in conventional cascaded systems, meaning that the training data most suited for the task cannot be used. Previous studies suggested several approaches for integrated end-to-end training to overcome those problems, however they mostly rely on (synthetic or natural) three-way data. We propose a cascaded model based on the non-autoregressive Transformer that enables end-to-end training without the need for an explicit intermediate representation. This new architecture (i) avoids unnecessary early decisions that can cause errors which are then propagated throughout the cascaded models and (ii) utilizes the end-to-end training data directly. We conduct an evaluation on two pivot-based machine translation tasks, namely French-German and German-Czech. Our experimental results show that the proposed architecture yields an improvement of more than 2 BLEU for French-German over the cascaded baseline.

📄 PDF Abstract BibTeX arXiv:2109.12950

Code (0)

등록된 구현이 없습니다.

Tasks

Machine TranslationTranslation

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Position-Wise Feed-Forward Layer 설명 없음
Adam 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

Similar Papers 제목 키워드 기반

Autoregressive model path dependence near Ising criticality

2024-08-28 · Yi Hong Teoh, Roger G. Melko

Autoregressive models are a class of generative model that probabilistically predict the next output of a sequence based on previous inputs. The autoregressive sequence is by definition one-dimensional (1D), which is nat…

model

Fast Decoding in Sequence Models using Discrete Latent Variables

2018-03-09 · ICML 2018 7 · Łukasz Kaiser, Aurko Roy, Ashish Vaswani, Niki Parmar 외

Autoregressive sequence models based on deep neural networks, such as RNNs, Wavenet and the Transformer attain state-of-the-art results on many tasks. However, they are difficult to parallelize and are thus slow at proce…

Machine TranslationTranslation

Spike-Triggered Non-Autoregressive Transformer for End-to-End Speech Recognition

2020-05-16 · Zhengkun Tian, Jiangyan Yi, Jian-Hua Tao, Ye Bai 외

Non-autoregressive transformer models have achieved extremely fast inference speed and comparable performance with autoregressive sequence-to-sequence models in neural machine translation. Most of the non-autoregressive …

Machine Translationspeech-recognitionSpeech RecognitionTranslation

Pose Transformers (POTR): Human Motion Prediction with Non-Autoregressive Transformers

2021-09-15 · Angel Martínez-González, Michael Villamizar, Jean-Marc Odobez

We propose to leverage Transformer architectures for non-autoregressive human motion prediction. Our approach decodes elements in parallel from a query sequence, instead of conditioning on previous predictions such as in…

ClassificationHuman motion predictionmotion prediction

Parallelizing Autoregressive Generation with Variational State Space Models

2024-07-11 · Gaspard Lambrechts, Yann Claes, Pierre Geurts, Damien Ernst

Attention-based models such as Transformers and recurrent models like state space models (SSMs) have emerged as successful methods for autoregressive sequence modeling. Although both enable parallel training, none enable…

DecoderMambaState Space ModelsText Generation