# Memory-enhanced Decoder for Neural Machine Translation

arXiv: https://arxiv.org/abs/1606.02003 · HTML: https://mlsanity.com/paper/1606.02003/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Jun 2016.

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

- [Adaptive Memory Networks with Self-supervised Learning for Unsupervised Anomaly Detection](https://mlsanity.com/paper/2201.00464/) (2022)
- [Informative Text Generation from Knowledge Triples](https://mlsanity.com/paper/2209.12733/) (2022)

## Abstract (arXiv)

We propose to enhance the RNN decoder in a neural machine translator (NMT) with external memory, as a natural but powerful extension to the state in the decoding RNN. This memory-enhanced RNN decoder is called textscMemDec. At each time during decoding, textscMemDec will read from this memory and write to this memory once, both with content-based addressing. Unlike the unbounded memory in previous workciteRNNsearch to store the representation of source sentence, the memory in textscMemDec is a matrix with pre-determined size designed to better capture the information important for the decoding process at each time step. Our empirical study on Chinese-English translation shows that it can improve by 4.8 BLEU upon Groundhog and 5.3 BLEU upon on Moses, yielding the best performance achieved with the same training set.