# Exploiting Semantics in Neural Machine Translation with Graph Convolutional Networks

arXiv: https://arxiv.org/abs/1804.08313 · HTML: https://mlsanity.com/paper/1804.08313/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Apr 2018.

## Built on by (most cited first, 30 of 30)

- [Compositional Generalization from First Principles](https://mlsanity.com/paper/2307.05596/) (2023)
- [Edge-Cloud Polarization and Collaboration: A Comprehensive Survey for AI](https://mlsanity.com/paper/2111.06061/) (2021)
- [Consensus Graph Representation Learning for Better Grounded Image Captioning](https://mlsanity.com/paper/2112.00974/) (2021)
- [Semantic Representation for Dialogue Modeling](https://mlsanity.com/paper/2105.10188/) (2021)
- [Privacy-Preserving Graph Convolutional Networks for Text Classification](https://mlsanity.com/paper/2102.09604/) (2021)
- [Feature Overcorrelation in Deep Graph Neural Networks: A New Perspective](https://mlsanity.com/paper/2206.07743/) (2022)
- [Efficient Graph Deep Learning in TensorFlow with tf_geometric](https://mlsanity.com/paper/2101.11552/) (2021)
- [Dynamic Interactive Relation Capturing via Scene Graph Learning for Robotic Surgical Report Generation](https://mlsanity.com/paper/2306.02651/) (2023)
- [Catastrophic Forgetting in Deep Graph Networks: an Introductory Benchmark for Graph Classification](https://mlsanity.com/paper/2103.11750/) (2021)
- [Relational Graph Learning for Grounded Video Description Generation](https://mlsanity.com/paper/2112.00967/) (2021)
- [Generic and Trend-aware Curriculum Learning for Relation Extraction in Graph Neural Networks](https://mlsanity.com/paper/2205.08625/) (2022)
- [GRANITE: A Graph Neural Network Model for Basic Block Throughput Estimation](https://mlsanity.com/paper/2210.03894/) (2022)
- [Conversational Semantic Role Labeling](https://mlsanity.com/paper/2104.04947/) (2021)
- [Semantics-aware Attention Improves Neural Machine Translation](https://mlsanity.com/paper/2110.06920/) (2021)
- [Semantic Role Labeling Meets Definition Modeling: Using Natural Language to Describe Predicate-Argument Structures](https://mlsanity.com/paper/2212.01094/) (2022)
- [Graph Feature Gating Networks](https://mlsanity.com/paper/2105.04493/) (2021)
- [Position-based Hash Embeddings For Scaling Graph Neural Networks](https://mlsanity.com/paper/2109.00101/) (2021)
- [Transition-based Semantic Role Labeling with Pointer Networks](https://mlsanity.com/paper/2205.10023/) (2022)
- [Neural Machine Translation with Dynamic Graph Convolutional Decoder](https://mlsanity.com/paper/2305.17698/) (2023)
- [Graph Classification via Discriminative Edge Feature Learning](https://mlsanity.com/paper/2210.02060/) (2022)
- [Enhancing the Transformer Decoder with Transition-based Syntax](https://mlsanity.com/paper/2101.12640/) (2021)
- [Fast and Accurate End-to-End Span-based Semantic Role Labeling as Word-based Graph Parsing](https://mlsanity.com/paper/2112.02970/) (2021)
- [ViCGCN: Graph Convolutional Network with Contextualized Language Models for Social Media Mining in Vietnamese](https://mlsanity.com/paper/2309.02902/) (2023)
- [PipeNet: Question Answering with Semantic Pruning over Knowledge Graphs](https://mlsanity.com/paper/2401.17536/) (2024)
- [Entity-Aware Self-Attention and Contextualized GCN for Enhanced Relation Extraction in Long Sentences](https://mlsanity.com/paper/2409.13755/) (2024)
- [LLMs Can Also Do Well! Breaking Barriers in Semantic Role Labeling via Large Language Models](https://mlsanity.com/paper/2506.05385/) (2025)
- [A Knowledge Enhanced Learning and Semantic Composition Model for Multi-Claim Fact Checking](https://mlsanity.com/paper/2104.13046/) (2021)
- [Development of Human Motion Prediction Strategy using Inception Residual Block](https://mlsanity.com/paper/2108.04001/) (2021)
- [Exploring Non-Verbal Predicates in Semantic Role Labeling: Challenges and Opportunities](https://mlsanity.com/paper/2307.01870/) (2023)
- [Generated Contents Enrichment](https://mlsanity.com/paper/2405.03650/) (2024)

## Abstract (arXiv)

Semantic representations have long been argued as potentially useful for enforcing meaning preservation and improving generalization performance of machine translation methods. In this work, we are the first to incorporate information about predicate-argument structure of source sentences (namely, semantic-role representations) into neural machine translation. We use Graph Convolutional Networks (GCNs) to inject a semantic bias into sentence encoders and achieve improvements in BLEU scores over the linguistic-agnostic and syntax-aware versions on the English--German language pair.