Papers
arxiv:1906.09601

Sequence Generation: From Both Sides to the Middle

Published on Jun 23, 2019
Authors:
,
,
,

Abstract

A synchronous bidirectional sequence generation model accelerates decoding and improves quality in machine translation and text summarization by predicting outputs from both directions simultaneously with interactive attention mechanisms.

AI-generated summary

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 from left to right, hence (1) this autoregressive decoding procedure is time-consuming when the output sentence becomes longer, and (2) it lacks the guidance of future context which is crucial to avoid under translation. To alleviate these issues, we propose a synchronous bidirectional sequence generation (SBSG) model which predicts its outputs from both sides to the middle simultaneously. In the SBSG model, we enable the left-to-right (L2R) and right-to-left (R2L) generation to help and interact with each other by leveraging interactive bidirectional attention network. Experiments on neural machine translation (En-De, Ch-En, and En-Ro) and text summarization tasks show that the proposed model significantly speeds up decoding while improving the generation quality compared to the autoregressive Transformer.

Community

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/1906.09601 in a model README.md to link it from this page.

Datasets citing this paper 1

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/1906.09601 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.