# Chunk-Based Bi-Scale Decoder for Neural Machine Translation

arXiv: https://arxiv.org/abs/1705.01452 · HTML: https://mlsanity.com/paper/1705.01452/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 May 2017.

## Built on by (most cited first, 2 of 2)

- [Deps-SAN: Neural Machine Translation with Dependency-Scaled Self-Attention Network](https://mlsanity.com/paper/2111.11707/) (2021)
- [Understanding the effects of word-level linguistic annotations in under-resourced neural machine translation](https://mlsanity.com/paper/2401.16078/) (2024)

## Abstract (arXiv)

In typical neural machine translation~(NMT), the decoder generates a sentence word by word, packing all linguistic granularities in the same time-scale of RNN. In this paper, we propose a new type of decoder for NMT, which splits the decode state into two parts and updates them in two different time-scales. Specifically, we first predict a chunk time-scale state for phrasal modeling, on top of which multiple word time-scale states are generated. In this way, the target sentence is translated hierarchically from chunks to words, with information in different granularities being leveraged. Experiments show that our proposed model significantly improves the translation performance over the state-of-the-art NMT model.