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

arXiv: https://arxiv.org/abs/1911.10438 · HTML: https://mlsanity.com/paper/1911.10438/

## Key facts

- Cited by 47 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Nov 2019.

## Built on by (most cited first, 30 of 47)

- [Revisiting Relation Extraction in the era of Large Language Models](https://mlsanity.com/paper/2305.05003/) (2023)
- [Multi-Task Learning in Natural Language Processing: An Overview](https://mlsanity.com/paper/2109.09138/) (2021)
- [Generative Knowledge Graph Construction: A Review](https://mlsanity.com/paper/2210.12714/) (2022)
- [Summarization as Indirect Supervision for Relation Extraction](https://mlsanity.com/paper/2205.09837/) (2022)
- [OneRel:Joint Entity and Relation Extraction with One Module in One Step](https://mlsanity.com/paper/2203.05412/) (2022)
- [A sequence-to-sequence approach for document-level relation extraction](https://mlsanity.com/paper/2204.01098/) (2022)
- [A Comprehensive Survey on Relation Extraction: Recent Advances and New Frontiers](https://mlsanity.com/paper/2306.02051/) (2023)
- [A Novel Global Feature-Oriented Relational Triple Extraction Model based on Table Filling](https://mlsanity.com/paper/2109.06705/) (2021)
- [Discovering Drug-Target Interaction Knowledge from Biomedical Literature](https://mlsanity.com/paper/2109.13187/) (2021)
- [A Simple but Effective Bidirectional Framework for Relational Triple Extraction](https://mlsanity.com/paper/2112.04940/) (2021)
- [Deep Neural Approaches to Relation Triplets Extraction: A Comprehensive Survey](https://mlsanity.com/paper/2103.16929/) (2021)
- [Information Extraction in Low-Resource Scenarios: Survey and Perspective](https://mlsanity.com/paper/2202.08063/) (2022)
- [InstructIE: A Bilingual Instruction-based Information Extraction Dataset](https://mlsanity.com/paper/2305.11527/) (2023)
- [Rescue Implicit and Long-tail Cases: Nearest Neighbor Relation Extraction](https://mlsanity.com/paper/2210.11800/) (2022)
- [HySPA: Hybrid Span Generation for Scalable Text-to-Graph Extraction](https://mlsanity.com/paper/2106.15838/) (2021)
- [FactReranker: Fact-guided Reranker for Faithful Radiology Report Summarization](https://mlsanity.com/paper/2303.08335/) (2023)
- [A Generative Model for Relation Extraction and Classification](https://mlsanity.com/paper/2202.13229/) (2022)
- [Query-based Instance Discrimination Network for Relational Triple Extraction](https://mlsanity.com/paper/2211.01797/) (2022)
- [Relation Extraction with Weighted Contrastive Pre-training on Distant Supervision](https://mlsanity.com/paper/2205.08770/) (2022)
- [AlpaPICO: Extraction of PICO Frames from Clinical Trial Documents Using LLMs](https://mlsanity.com/paper/2409.09704/) (2024)
- [REKnow: Enhanced Knowledge for Joint Entity and Relation Extraction](https://mlsanity.com/paper/2206.05123/) (2022)
- [End-to-End n-ary Relation Extraction for Combination Drug Therapies](https://mlsanity.com/paper/2303.16886/) (2023)
- [Adjacency List Oriented Relational Fact Extraction via Adaptive Multi-task Learning](https://mlsanity.com/paper/2106.01559/) (2021)
- [BioCopy: A Plug-And-Play Span Copy Mechanism in Seq2Seq Models](https://mlsanity.com/paper/2109.12533/) (2021)
- [Relational Triple Extraction: One Step is Enough](https://mlsanity.com/paper/2205.05270/) (2022)
- [Training on Synthetic Data Beats Real Data in Multimodal Relation Extraction](https://mlsanity.com/paper/2312.03025/) (2023)
- [A Benchmark for End-to-End Zero-Shot Biomedical Relation Extraction with LLMs: Experiments with OpenAI Models](https://mlsanity.com/paper/2504.04083/) (2025)
- [A Cascade Dual-Decoder Model for Joint Entity and Relation Extraction](https://mlsanity.com/paper/2106.14163/) (2021)
- [Triples-to-Text Generation with Reinforcement Learning Based Graph-augmented Neural Networks](https://mlsanity.com/paper/2111.10545/) (2021)
- [CEntRE: A paragraph-level Chinese dataset for Relation Extraction among Enterprises](https://mlsanity.com/paper/2210.10581/) (2022)

## Abstract (arXiv)

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. textitSteven 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