# N-ary Relation Extraction using Graph State LSTM

arXiv: https://arxiv.org/abs/1808.09101 · HTML: https://mlsanity.com/paper/1808.09101/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Aug 2018.

## Built on by (most cited first, 26 of 26)

- [Entity Structure Within and Throughout: Modeling Mention Dependencies for Document-Level Relation Extraction](https://mlsanity.com/paper/2102.10249/) (2021)
- [FormNet: Structural Encoding beyond Sequential Modeling in Form Document Information Extraction](https://mlsanity.com/paper/2203.08411/) (2022)
- [SIRE: Separate Intra- and Inter-sentential Reasoning for Document-level Relation Extraction](https://mlsanity.com/paper/2106.01709/) (2021)
- [A sequence-to-sequence approach for document-level relation extraction](https://mlsanity.com/paper/2204.01098/) (2022)
- [Uncovering Main Causalities for Long-tailed Information Extraction](https://mlsanity.com/paper/2109.05213/) (2021)
- [Inspecting the concept knowledge graph encoded by modern language models](https://mlsanity.com/paper/2105.13471/) (2021)
- [Deep Neural Approaches to Relation Triplets Extraction: A Comprehensive Survey](https://mlsanity.com/paper/2103.16929/) (2021)
- [BERT-GT: Cross-sentence n-ary relation extraction with BERT and Graph Transformer](https://mlsanity.com/paper/2101.04158/) (2021)
- [Discourse-level Relation Extraction via Graph Pooling](https://mlsanity.com/paper/2101.00124/) (2021)
- [GenKIE: Robust Generative Multimodal Document Key Information Extraction](https://mlsanity.com/paper/2310.16131/) (2023)
- [Supporting Medical Relation Extraction via Causality-Pruned Semantic Dependency Forest](https://mlsanity.com/paper/2208.13472/) (2022)
- [Graph Learning and Its Advancements on Large Language Models: A Holistic Survey](https://mlsanity.com/paper/2212.08966/) (2022)
- [A Comprehensive Survey of Document-level Relation Extraction (2016-2023)](https://mlsanity.com/paper/2309.16396/) (2023)
- [A Survey of Document-Level Information Extraction](https://mlsanity.com/paper/2309.13249/) (2023)
- [AI perspectives in Smart Cities and Communities to enable road vehicle automation and smart traffic control](https://mlsanity.com/paper/2104.03150/) (2021)
- [GraphRevisedIE: Multimodal Information Extraction with Graph-Revised Network](https://mlsanity.com/paper/2410.01160/) (2024)
- [Speaker-Oriented Latent Structures for Dialogue-Based Relation Extraction](https://mlsanity.com/paper/2109.05182/) (2021)
- [Modeling Multi-Granularity Hierarchical Features for Relation Extraction](https://mlsanity.com/paper/2204.04437/) (2022)
- [Entity-Aware Self-Attention and Contextualized GCN for Enhanced Relation Extraction in Long Sentences](https://mlsanity.com/paper/2409.13755/) (2024)
- [Multi-Scale Feature and Metric Learning for Relation Extraction](https://mlsanity.com/paper/2107.13425/) (2021)
- [Pruned Graph Neural Network for Short Story Ordering](https://mlsanity.com/paper/2203.06778/) (2022)
- [Comparative Analysis of Contextual Relation Extraction based on Deep Learning Models](https://mlsanity.com/paper/2309.06814/) (2023)
- [Do the Benefits of Joint Models for Relation Extraction Extend to Document-level Tasks?](https://mlsanity.com/paper/2310.00696/) (2023)
- [Augmenting Document-level Relation Extraction with Efficient Multi-Supervision](https://mlsanity.com/paper/2407.01026/) (2024)
- [VRDSynth: Synthesizing Programs for Multilingual Visually Rich Document Information Extraction](https://mlsanity.com/paper/2407.06826/) (2024)
- [RexDrug: Reliable Multi-Drug Combination Extraction through Reasoning-Enhanced LLMs](https://mlsanity.com/paper/2603.08166/) (2026)

## Abstract (arXiv)

Cross-sentence n-ary relation extraction detects relations among n entities across multiple sentences. Typical methods formulate an input as a textitdocument graph, integrating various intra-sentential and inter-sentential dependencies. The current state-of-the-art method splits the input graph into two DAGs, adopting a DAG-structured LSTM for each. Though being able to model rich linguistic knowledge by leveraging graph edges, important information can be lost in the splitting procedure. We propose a graph-state LSTM model, which uses a parallel state to model each word, recurrently enriching state values via message passing. Compared with DAG LSTMs, our graph LSTM keeps the original graph structure, and speeds up computation by allowing more parallelization. On a standard benchmark, our model shows the best result in the literature.