Modeling Joint Entity and Relation Extraction with Table Representation

By Makoto Miwa, Yutaka Sasaki. Conference on Empirical Methods in Natural Language Processing, 2014

338 citations recorded by the source corpus.

This paper proposes a history-based structured learning approach that jointly extracts entities and relations in a sentence. We introduce a novel simple and flexible table representation of entities and relations. We investigate several feature settings, search orders, and learning methods with inexact search on the table. The experimental results demonstrate that a joint learning approach significantly outperforms a pipeline approach by incorporating global features and by selecting appropriate learning methods and search orders.

Subfields: Artificial Intelligence, Information Systems

View Paper: https://www.semanticscholar.org/paper/1845a57621ba2ce9ff3c2d1dcaa1f7f4b04b2186

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Mohit Bansal
2. Xiang Ren
3. Philip S. Yu
4. Heng Ji
5. Erik Cambria
6. Danqi Chen
7. Zhiyuan Liu
8. Jianfeng Gao

In Information Systems

1. Philip S. Yu
2. Claire Cardie
3. Heng Ji
4. Jiawei Han
5. Lidong Bing
6. Xiang Ren
7. Danqi Chen
8. Zexuan Zhong

Citations in the corpus

• Span-based Joint Entity and Relation Extraction with Transformer Pre-training (2019, background): “Miwa and Sasaki [23] tackle joint entity and relation extraction as a table-filling problem, where each cell of the table corresponds to a word pair of the sentence.”
• A Joint Neural Model for Information Extraction with Global Features (2020, methodology): “As a solution, some researchers propose joint inference and joint modeling methods to improve local prediction (Roth and Yih, 2004; Ji and Grishman, 2005; Ji et al., 2005; Sil and Yates, 2013; Li et al., 2014; Durrett and Klein, 2014; Miwa and Sasaki, 2014; Lu and Roth, 2015; Yang and Mitchell, 2016”
• End-to-End Relation Extraction using LSTMs on Sequences and Tree Structures (2016, methodology): “…and Roth, 2009) and relation extraction (Zelenko et al., 2003; Zhou et al., 2005), but recent studies show that end-to-end (joint) modeling of entity and relation is important for high performance (Li and Ji, 2014; Miwa and Sasaki, 2014) since relations interact closely with entity information.”
• CoType: Joint Extraction of Typed Entities and Relations with Knowledge Bases (2016, background): “existing joint extraction methods [24, 32]), and models entityrelation interactions jointly with other signals to resolve error propagation (vs.”
• Joint entity recognition and relation extraction as a multi-head selection problem (2018, methodology): “Feature-based joint models (Kate & Mooney, 2010; Yang & Cardie, 2013; Li & Ji, 2014; Miwa & Sasaki, 2014) have been proposed to simultaneously solve the entity recognition and relation extraction (RE) subtasks.”
• A Survey on Knowledge Graphs: Representation, Acquisition, and Applications (2020, background): “Several studies show better performance by joint learning [143], [166] than by conventional pipeline methods.”
• Entity-Relation Extraction as Multi-Turn Question Answering (2019, methodology): “Miwa and Sasaki (2014); Gupta et al. (2016); Zhang et al. (2017) proposed the table-filling approach, which provides an opportunity to incorporating more sophisticated features and algorithms into the model, such as search orders in decoding and global features.”
• Joint Extraction of Entities and Relations Based on a Novel Tagging Scheme (2017, methodology): “Most of the joint methods are feature-based structured systems (Ren et al., 2017; Yang and Cardie, 2013; Singh et al., 2013; Miwa and Sasaki, 2014; Li and Ji, 2014).”
• Joint Event and Temporal Relation Extraction with Shared Representations and Structured Prediction (2019, background): “Miwa and Sasaki (2014) frame their joint model as table filling tasks, map tabular representation into sequential predictions with heuristic rules, and construct global loss to compute the best joint predictions.”
• GraphRel: Modeling Text as Relational Graphs for Joint Entity and Relation Extraction (2019, methodology): “Joint entity recognition and relation extraction models (Yu and Lam, 2010; Li and Ji, 2014; Miwa and Sasaki, 2014; Ren et al., 2017) have been built to take advantage of the close interaction between these two tasks.”
• Going out on a limb: Joint Extraction of Entity Mentions and Relations without Dependency Trees (2017, methodology): “…models that treat the identification of entity mentions (Nadeau and Sekine, 2007) and relation classification (Zhou et al., 2005) as two separate tasks; and 2) joint models, also the more recent, which simultaneously identify the entity mention and relations (Li and Ji, 2014; Miwa and Sasaki, 2014).”
• Assessing The Factual Accuracy of Generated Text (2019, methodology): “s article-level information that can be used to train models like in Section 4.2. Since using two-step processes may be affected by compounding of errors across the models, some end-to-end approaches [18, 19] have been proposed, where the models extract entities and relations in one pass through the”
• Position-Aware Tagging for Aspect Sentiment Triplet Extraction (2020, methodology): “Miwa and Sasaki (2014) and Li and Ji (2014) used approaches motivated by a table-filling method to jointly extract entity pairs as well as their relations.”
• Extracting Relational Facts by an End-to-End Neural Model with Copy Mechanism (2018, background): “Early works (Yu and Lam, 2010; Li and Ji, 2014; Miwa and Sasaki, 2014) need complicated process of feature engineering and heavily depends on NLP tools for feature extraction.”
• A Frustratingly Easy Approach for Entity and Relation Extraction (2021, background): “In the last several years, there has been a surge of interest in developing models for joint extraction of entities and relations (Li and Ji, 2014; Miwa and Sasaki, 2014; Miwa and Bansal, 2016).”
• A Novel Cascade Binary Tagging Framework for Relational Triple Extraction (2019, methodology): “Traditional joint models (Yu and Lam, 2010; Li and Ji, 2014; Miwa and Sasaki, 2014; Ren et al., 2017) are feature-based, which heavily rely on feature engineering and require intensive manual efforts.”
• A Unified Model for Opinion Target Extraction and Target Sentiment Prediction (2018, background): “…in the text, and it has been extensively studied (Qiu et al. 2011; Liu, Xu, and Zhao 2013; As observed in some other tasks (Jing et al. 2003; Ng and Low 2004; Finkel and Manning 2009; Miwa and Sasaki 2014), if two sub-tasks have strong couplings (e.g, NER and relation extraction), a more…”