# Syntax-Aware Complex-Valued Neural Machine Translation

arXiv: https://arxiv.org/abs/2307.08586 · HTML: https://mlsanity.com/paper/2307.08586/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 25 references that are in the map.
- First posted on arXiv 17 Jul 2023.

## Builds on (most cited first, 13 of 13)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [On the Properties of Neural Machine Translation: Encoder-Decoder Approaches](https://mlsanity.com/paper/1409.1259/) (2014)
- [Effective Approaches to Attention-based Neural Machine Translation](https://mlsanity.com/paper/1508.04025/) (2015)
- [Deep Complex Networks](https://mlsanity.com/paper/1705.09792/) (2017)
- [End-to-End Relation Extraction using LSTMs on Sequences and Tree Structures](https://mlsanity.com/paper/1601.00770/) (2016)
- [Encoding word order in complex embeddings](https://mlsanity.com/paper/1912.12333/) (2019)
- [Quaternion Convolutional Neural Networks](https://mlsanity.com/paper/1903.00658/) (2019)
- [Better than Real: Complex-valued Neural Nets for MRI Fingerprinting](https://mlsanity.com/paper/1707.00070/) (2017)
- [Improved Neural Machine Translation with a Syntax-Aware Encoder and Decoder](https://mlsanity.com/paper/1707.05436/) (2017)
- [Structural Attention Neural Networks for improved sentiment analysis](https://mlsanity.com/paper/1701.01811/) (2017)
- [Semantic Hilbert Space for Text Representation Learning](https://mlsanity.com/paper/1902.09802/) (2019)
- [Neural Machine Translation with Source-Side Latent Graph Parsing](https://mlsanity.com/paper/1702.02265/) (2017)

## Abstract (arXiv)

Syntax has been proven to be remarkably effective in neural machine translation (NMT). Previous models obtained syntax information from syntactic parsing tools and integrated it into NMT models to improve translation performance. In this work, we propose a method to incorporate syntax information into a complex-valued Encoder-Decoder architecture. The proposed model jointly learns word-level and syntax-level attention scores from the source side to the target side using an attention mechanism. Importantly, it is not dependent on specific network architectures and can be directly integrated into any existing sequence-to-sequence (Seq2Seq) framework. The experimental results demonstrate that the proposed method can bring significant improvements in BLEU scores on two datasets. In particular, the proposed method achieves a greater improvement in BLEU scores in translation tasks involving language pairs with significant syntactic differences.