Enriched Attention for Robust Relation Extraction
Not on the map. Why?
Abstract (arXiv)
The performance of relation extraction models has increased considerably with the rise of neural networks. However, a key issue of neural relation extraction is robustness: the models do not scale well to long sentences with multiple entities and relations. In this work, we address this problem with an enriched attention mechanism. Attention allows the model to focus on parts of the input sentence that are relevant to relation extraction. We propose to enrich the attention function with features modeling knowledge about the relation arguments and the shortest dependency path between them. Thus, for different relation arguments, the model can pay attention to different parts of the sentence. Our model outperforms prior work using comparable setups on two popular benchmarks, and our analysis confirms that it indeed scales to long sentences with many entities.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 26 of its 53 references that are in the map. First posted on arXiv 22 Apr 2021.
Builds on
26 of 53 references.
References · 26
- 2017Attention Is All You Needcited by 59,932
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
- 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
- 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,907
- 2018Deep contextualized word representationscited by 2,285
- 2016Neural Architectures for Named Entity Recognitioncited by 548
- 2019Matching the Blanks: Distributional Similarity for Relation Learningcited by 271
- 2016End-to-End Relation Extraction using LSTMs on Sequences and Tree Structurescited by 161
- 2018Graph Convolution over Pruned Dependency Trees Improves Relation Extractioncited by 146
- 2019Entity-Relation Extraction as Multi-Turn Question Answeringcited by 96
- 2019A General Framework for Information Extraction using Dynamic Span Graphscited by 93
- 2019Knowledge-Enriched Transformer for Emotion Detection in Textual Conversationscited by 92
14 more
- 2019Attention Guided Graph Convolutional Networks for Relation Extractioncited by 82
- 2017BPEmb: Tokenization-free Pre-trained Subword Embeddings in 275 Languagescited by 52
- 2015Classifying Relations via Long Short Term Memory Networks along Shortest Dependency Pathcited by 35
- 2016CoType: Joint Extraction of Typed Entities and Relations with Knowledge Basescited by 28
- 2019Improving Relation Extraction by Pre-trained Language Representationscited by 24
- 2019Exploiting Entity BIO Tag Embeddings and Multi-task Learning for Relation Extraction with Imbalanced Datacited by 11
- 2017Learning Distributed Representations of Texts and Entities from Knowledge Basecited by 10
- 2019A Walk-based Model on Entity Graphs for Relation Extractioncited by 8
- 2016Exploring Different Dimensions of Attention for Uncertainty Detectioncited by 7
- 2017Improving Slot Filling Performance with Attentive Neural Networks on Dependency Structurescited by 7
- 2017Corpus-level Fine-grained Entity Typingcited by 7
- 2019Improving Relation Extraction with Knowledge-attentioncited by 6
- 2019Type-aware Convolutional Neural Networks for Slot Fillingcited by 3
- 2015Combining Neural Networks and Log-linear Models to Improve Relation Extractioncited by 2
Built on by
Citing papers per year: 2023: 1.
1 paper.