# Towards Linear Time Neural Machine Translation with Capsule Networks

arXiv: https://arxiv.org/abs/1811.00287 · HTML: https://mlsanity.com/paper/1811.00287/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Nov 2018.

## Built on by (most cited first, 4 of 4)

- [Learning Language Specific Sub-network for Multilingual Machine Translation](https://mlsanity.com/paper/2105.09259/) (2021)
- [Turning Fixed to Adaptive: Integrating Post-Evaluation into Simultaneous Machine Translation](https://mlsanity.com/paper/2210.11900/) (2022)
- [Shifting Capsule Networks from the Cloud to the Deep Edge](https://mlsanity.com/paper/2110.02911/) (2021)
- [UPB at SemEval-2021 Task 7: Adversarial Multi-Task Learning for Detecting and Rating Humor and Offense](https://mlsanity.com/paper/2104.06063/) (2021)

## Abstract (arXiv)

In this study, we first investigate a novel capsule network with dynamic routing for linear time Neural Machine Translation (NMT), referred as textscCapsNMT. textscCapsNMT uses an aggregation mechanism to map the source sentence into a matrix with pre-determined size, and then applys a deep LSTM network to decode the target sequence from the source representation. Unlike the previous work citesutskever2014sequence to store the source sentence with a passive and bottom-up way, the dynamic routing policy encodes the source sentence with an iterative process to decide the credit attribution between nodes from lower and higher layers. textscCapsNMT has two core properties: it runs in time that is linear in the length of the sequences and provides a more flexible way to select, represent and aggregates the part-whole information of the source sentence. On WMT14 English-German task and a larger WMT14 English-French task, textscCapsNMT achieves comparable results with the state-of-the-art NMT systems. To the best of our knowledge, this is the first work that capsule networks have been empirically investigated for sequence to sequence problems.