mlsanityData to 7 Oct 2026

Exploiting Semantics in Neural Machine Translation with Graph Convolutional Networks

arXiv 1804.08313 ↗First posted 23 Apr 2018cs.CLcited by 30

Not on the map. Why?

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.

Key facts. Cited by 30 papers in the map (data through 7 Oct 2026). First posted on arXiv 23 Apr 2018.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 15; 2022: 6; 2023: 5; 2024: 3; 2025: 1.

30 papers.

Sort:

  1. 2023Compositional Generalization from First Principlescited by 62
  2. 2021Edge-Cloud Polarization and Collaboration: A Comprehensive Survey for AIcited by 38
  3. 2021Consensus Graph Representation Learning for Better Grounded Image Captioningcited by 28
  4. 2021Semantic Representation for Dialogue Modelingcited by 24
  5. 2021Privacy-Preserving Graph Convolutional Networks for Text Classificationcited by 19
  6. 2022Feature Overcorrelation in Deep Graph Neural Networks: A New Perspectivecited by 19
  7. 2021Efficient Graph Deep Learning in TensorFlow with tf_geometriccited by 17
  8. 2023Dynamic Interactive Relation Capturing via Scene Graph Learning for Robotic Surgical Report Generationcited by 14
  9. 2021Catastrophic Forgetting in Deep Graph Networks: an Introductory Benchmark for Graph Classificationcited by 13
  10. 2021Relational Graph Learning for Grounded Video Description Generationcited by 12
  11. 2022Generic and Trend-aware Curriculum Learning for Relation Extraction in Graph Neural Networkscited by 9
  12. 2022GRANITE: A Graph Neural Network Model for Basic Block Throughput Estimationcited by 9
18 more
  1. 2021Conversational Semantic Role Labelingcited by 8
  2. 2021Semantics-aware Attention Improves Neural Machine Translationcited by 5
  3. 2022Semantic Role Labeling Meets Definition Modeling: Using Natural Language to Describe Predicate-Argument Structurescited by 4
  4. 2021Graph Feature Gating Networkscited by 3
  5. 2021Position-based Hash Embeddings For Scaling Graph Neural Networkscited by 3
  6. 2022Transition-based Semantic Role Labeling with Pointer Networkscited by 3
  7. 2022Graph Classification via Discriminative Edge Feature Learningcited by 2
  8. 2023Neural Machine Translation with Dynamic Graph Convolutional Decodercited by 2
  9. 2021Enhancing the Transformer Decoder with Transition-based Syntaxcited by 1
  10. 2021Fast and Accurate End-to-End Span-based Semantic Role Labeling as Word-based Graph Parsingcited by 1
  11. 2023ViCGCN: Graph Convolutional Network with Contextualized Language Models for Social Media Mining in Vietnamesecited by 1
  12. 2024PipeNet: Question Answering with Semantic Pruning over Knowledge Graphscited by 1
  13. 2024Entity-Aware Self-Attention and Contextualized GCN for Enhanced Relation Extraction in Long Sentencescited by 1
  14. 2025LLMs Can Also Do Well! Breaking Barriers in Semantic Role Labeling via Large Language Modelscited by 1
  15. 2021A Knowledge Enhanced Learning and Semantic Composition Model for Multi-Claim Fact Checkingcited by 0
  16. 2021Development of Human Motion Prediction Strategy using Inception Residual Blockcited by 0
  17. 2023Exploring Non-Verbal Predicates in Semantic Role Labeling: Challenges and Opportunitiescited by 0
  18. 2024Generated Contents Enrichmentcited by 0