A Walk-based Model on Entity Graphs for Relation Extraction

Christopoulou, Fenia; Misawa, Miwa; Ananiadou, Sophia

doi:10.18653/v1/p18-2014

Cited by 87 publications

(62 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…HRCNN (Kim and Choi, 2018) Network (FNN). WALK is a graph-based neural network model for relation extraction (Fenia et al, 2019). As shown in Table 1, the proposed model outperformed all comparison models.…”

Section: Datasets and Experimental Settingsmentioning

confidence: 95%

Relation Extraction among Multiple Entities Using a Dual Pointer Network with a Multi-Head Attention Mechanism

Park¹,

Kim²

2019

Proceedings of the Second Workshop on Fact Extraction and VERification (FEVER)

View full text Add to dashboard Cite

Many previous studies on relation extraction have been focused on finding only one relation between two entities in a single sentence. However, we can easily find the fact that multiple entities exist in a single sentence and the entities form multiple relations. To resolve this problem, we propose a relation extraction model based on a dual pointer network with a multi-head attention mechanism. The proposed model finds n-to-1 subject-object relations by using a forward decoder called an object decoder. Then, it finds 1-ton subject-object relations by using a backward decoder called a subject decoder. In the experiments with the ACE-05 dataset and the NYT dataset, the proposed model achieved the state-of-the-art performances (F1-score of 80.5% in the ACE-05 dataset, F1-score of 78.3% in the NYT dataset)

show abstract

Section: Datasets and Experimental Settingsmentioning

confidence: 95%

Relation Extraction among Multiple Entities Using a Dual Pointer Network with a Multi-Head Attention Mechanism

Park¹,

Kim²

2019

Proceedings of the Second Workshop on Fact Extraction and VERification (FEVER)

View full text Add to dashboard Cite

show abstract

“…For this purpose, we adapt our two-step inference mechanism, proposed in Christopoulou et al (2018), to encode interactions between nodes and edges in the graph and hence model EE associations.…”

Section: Inference Layermentioning

confidence: 99%

Connecting the Dots: Document-level Neural Relation Extraction with Edge-oriented Graphs

Christopoulou¹,

Misawa²,

Ananiadou³

2019

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conferen

Self Cite

163

View full text Add to dashboard Cite

Document-level relation extraction is a complex human process that requires logical inference to extract relationships between named entities in text. Existing approaches use graphbased neural models with words as nodes and edges as relations between them, to encode relations across sentences. These models are node-based, i.e., they form pair representations based solely on the two target node representations. However, entity relations can be better expressed through unique edge representations formed as paths between nodes. We thus propose an edge-oriented graph neural model for document-level relation extraction.

show abstract

“…Generally, these models consist of an encoder followed by a relationship classification (RC) unit (Verga et al, 2018;Christopoulou et al, 2018; * G. Singh was an intern at Amazon at the time of work Su et al, 2018). The encoder provides contextaware vector representations for both target entities, which are then merged or concatenated before being passed to the relation classification unit, where a two layered neural network or multilayered perceptron classifies the pair into different relation types.…”

Section: Introductionmentioning

confidence: 99%

Relation Extraction using Explicit Context Conditioning

Singh¹,

Bhatia²

2019

Proceedings of the 2019 Conference of the North

View full text Add to dashboard Cite

Relation Extraction (RE) aims to label relations between groups of marked entities in raw text. Most current RE models learn context-aware representations of the target entities that are then used to establish relation between them. This works well for intrasentence RE and we call them first-order relations. However, this methodology can sometimes fail to capture complex and long dependencies. To address this, we hypothesize that at times two target entities can be explicitly connected via a context token. We refer to such indirect relations as second-order relations and describe an efficient implementation for computing them. These second-order relation scores are then combined with first-order relation scores. Our empirical results show that the proposed method leads to state-of-theart performance over two biomedical datasets.

show abstract

A Walk-based Model on Entity Graphs for Relation Extraction

Cited by 87 publications

References 17 publications

Relation Extraction among Multiple Entities Using a Dual Pointer Network with a Multi-Head Attention Mechanism

Relation Extraction among Multiple Entities Using a Dual Pointer Network with a Multi-Head Attention Mechanism

Connecting the Dots: Document-level Neural Relation Extraction with Edge-oriented Graphs

Relation Extraction using Explicit Context Conditioning

Contact Info

Product

Resources

About