CopyMTL: Copy Mechanism for Joint Extraction of Entities and Relations with Multi-Task Learning

Abstract

Joint extraction of entities and relations has received significant attention due to its potential of providing higher performance for both tasks. Among existing methods, CopyRE is effective and novel, which uses a sequence-to-sequence framework and copy mechanism to directly generate the relation triplets. However, it suffers from two fatal problems. The model is extremely weak at differing the head and tail entity, resulting in inaccurate entity extraction. It also cannot predict multi-token entities (e.g. Steven Jobs). To address these problems, we give a detailed analysis of the reasons behind the inaccurate entity extraction problem, and then propose a simple but extremely effective model structure to solve this problem. In addition, we propose a multi-task learning framework equipped with copy mechanism, called CopyMTL, to allow the model to predict multi-token entities. Experiments reveal the problems of CopyRE and show that our model achieves significant improvement over the current state-of-the-art method by 9% in NYT and 16% in WebNLG (F1 score). Our code is available at https://github.com/WindChimeRan/CopyMTL

A Relational Adaptive Neural Model for Joint Entity and Relation Extraction

“…We compare the results with the MultiDecoder. • CopyMTL (Zeng et al, 2020) introduces a multi-task learning framework, which solves the problem of extracting only one word in CopeRe by adopting different strategies for the head entities, tail entities and relations in triples. • OrderRL (Zeng et al, 2019) regards the extraction of triples as a process of reinforcement learning (RL), explores the influence of the extraction order of triples, and the proposed sequence-to-sequence model can automatically learn and generate relational facts.…”

“…CopyMTL (Zeng et al, 2020 ) introduces a multi-task learning framework, which solves the problem of extracting only one word in CopeRe by adopting different strategies for the head entities, tail entities and relations in triples.…”

“…Yuan et al ( 2020 ) proposed a joint entity and relationship extraction model called RSAN, which combined the fine-grained semantic information of the relation to guide the entity recognition process. Zeng et al ( 2020 ) proposed their own improved model CopyMTL and introduced named entity task for multi-task learning based on CopyRE, thus improving the problem that CopyRE can only extract single words and cannot match multi-character entities. Hong et al ( 2020 ), based on GraphRel, proposed a new relational perceptive attention mechanism, which can acquire the representation of the relation between the span of two entities.…”

Recurrent Interaction Network for Jointly Extracting Entities and Classifying Relations

“…Recently, researchers have exploited multi-task learning (MTL) (Collobert and Weston, 2008) techniques to capture the correlation between the ER and RC tasks, and have successfully improved the performance of the individual tasks (Miwa and Bansal, 2016;Zeng et al, 2019a). These methods have a flat structure .…”

“…For example in Figure 1(a), the model cannot explicitly learn correlations between the two tasks. Without modeling explicit interactions, as shown in a sequence learning task , the existing MTL-based methods (Miwa and Bansal, 2016;Zeng et al, 2019a) cannot effectively capture the correlation between the ER and the RC tasks.…”