# RGAT: A Deeper Look into Syntactic Dependency Information for Coreference Resolution

arXiv: https://arxiv.org/abs/2309.04977 · HTML: https://mlsanity.com/paper/2309.04977/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 33 references that are in the map.
- First posted on arXiv 10 Sep 2023.

## Builds on (most cited first, 21 of 21)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Modeling Relational Data with Graph Convolutional Networks](https://mlsanity.com/paper/1703.06103/) (2017)
- [Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning](https://mlsanity.com/paper/1801.07606/) (2018)
- [LLM-Adapters: An Adapter Family for Parameter-Efficient Fine-Tuning of Large Language Models](https://mlsanity.com/paper/2304.01933/) (2023)
- [End-to-end Neural Coreference Resolution](https://mlsanity.com/paper/1707.07045/) (2017)
- [Higher-order Coreference Resolution with Coarse-to-fine Inference](https://mlsanity.com/paper/1804.05392/) (2018)
- [Encoding Sentences with Graph Convolutional Networks for Semantic Role Labeling](https://mlsanity.com/paper/1703.04826/) (2017)
- [BERT for Coreference Resolution: Baselines and Analysis](https://mlsanity.com/paper/1908.09091/) (2019)
- [Representation Learning for Attributed Multiplex Heterogeneous Network](https://mlsanity.com/paper/1905.01669/) (2019)
- [Anaphora and Coreference Resolution: A Review](https://mlsanity.com/paper/1805.11824/) (2018)
- [AdapterBias: Parameter-efficient Token-dependent Representation Shift for Adapters in NLP Tasks](https://mlsanity.com/paper/2205.00305/) (2022)
- [Learning Global Features for Coreference Resolution](https://mlsanity.com/paper/1604.03035/) (2016)
- [Resolving Gendered Ambiguous Pronouns with BERT](https://mlsanity.com/paper/1906.01161/) (2019)
- [The Referential Reader: A Recurrent Entity Network for Anaphora Resolution](https://mlsanity.com/paper/1902.01541/) (2019)
- [Look Again at the Syntax: Relational Graph Convolutional Network for Gendered Ambiguous Pronoun Resolution](https://mlsanity.com/paper/1905.08868/) (2019)
- [Gendered Ambiguous Pronouns Shared Task: Boosting Model Confidence by Evidence Pooling](https://mlsanity.com/paper/1906.00839/) (2019)

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

- [Building Foundations for Natural Language Processing of Historical Turkish: Resources and Models](https://mlsanity.com/paper/2501.04828/) (2025)
- [Sync-TVA: A Graph-Attention Framework for Multimodal Emotion Recognition with Cross-Modal Fusion](https://mlsanity.com/paper/2507.21395/) (2025)
- [Relationally Guided Use Case Modeling with LLMs](https://mlsanity.com/paper/2609.18291/) (2026)

## Abstract (arXiv)

Although syntactic information is beneficial for many NLP tasks, combining it with contextual information between words to solve the coreference resolution problem needs to be further explored. In this paper, we propose an end-to-end parser that combines pre-trained BERT with a Syntactic Relation Graph Attention Network (RGAT) to take a deeper look into the role of syntactic dependency information for the coreference resolution task. In particular, the RGAT model is first proposed, then used to understand the syntactic dependency graph and learn better task-specific syntactic embeddings. An integrated architecture incorporating BERT embeddings and syntactic embeddings is constructed to generate blending representations for the downstream task. Our experiments on a public Gendered Ambiguous Pronouns (GAP) dataset show that with the supervision learning of the syntactic dependency graph and without fine-tuning the entire BERT, we increased the F1-score of the previous best model (RGCN-with-BERT) from 80.3% to 82.5%, compared to the F1-score by single BERT embeddings from 78.5% to 82.5%. Experimental results on another public dataset - OntoNotes 5.0 demonstrate that the performance of the model is also improved by incorporating syntactic dependency information learned from RGAT.