# Neural Machine Translation with Source-Side Latent Graph Parsing

arXiv: https://arxiv.org/abs/1702.02265 · HTML: https://mlsanity.com/paper/1702.02265/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Feb 2017.

## Built on by (most cited first, 3 of 3)

- [AMR Parsing with Action-Pointer Transformer](https://mlsanity.com/paper/2104.14674/) (2021)
- [Visualizing the Relationship Between Encoded Linguistic Information and Task Performance](https://mlsanity.com/paper/2203.15860/) (2022)
- [Syntax-Aware Complex-Valued Neural Machine Translation](https://mlsanity.com/paper/2307.08586/) (2023)

## Abstract (arXiv)

This paper presents a novel neural machine translation model which jointly learns translation and source-side latent graph representations of sentences. Unlike existing pipelined approaches using syntactic parsers, our end-to-end model learns a latent graph parser as part of the encoder of an attention-based neural machine translation model, and thus the parser is optimized according to the translation objective. In experiments, we first show that our model compares favorably with state-of-the-art sequential and pipelined syntax-based NMT models. We also show that the performance of our model can be further improved by pre-training it with a small amount of treebank annotations. Our final ensemble model significantly outperforms the previous best models on the standard English-to-Japanese translation dataset.