A Unified Generative Framework for Various NER Subtasks

By Hang Yan, Tao Gui, Junqi Dai, Qipeng Guo, Zheng Zhang, Xipeng Qiu. Annual Meeting of the Association for Computational Linguistics, 2021

366 citations recorded by the source corpus.

Named Entity Recognition (NER) is the task of identifying spans that represent entities in sentences. Whether the entity spans are nested or discontinuous, the NER task can be categorized into the flat NER, nested NER, and discontinuous NER subtasks. These subtasks have been mainly solved by the token-level sequence labelling or span-level classification. However, these solutions can hardly tackle the three kinds of NER subtasks concurrently. To that end, we propose to formulate the NER subtasks as an entity span sequence generation task, which can be solved by a unified sequence-to-sequence (Seq2Seq) framework. Based on our unified framework, we can leverage the pre-trained Seq2Seq model to solve all three kinds of NER subtasks without the special design of the tagging schema or ways to enumerate spans. We exploit three types of entity representations to linearize entities into a sequence. Our proposed framework is easy-to-implement and achieves state-of-the-art (SoTA) or near SoTA performance on eight English NER datasets, including two flat NER datasets, three nested NER datasets, and three discontinuous NER datasets.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/c09ff6965322ece56bce383266c75159234f59c4

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. Linhao Luo
2. Chong Teng
3. Donghong Ji
4. Xindong Wu
5. Shengqiong Wu
6. Jingye Li
7. Fei Li
8. Chen Chen

In Computer Vision and Pattern Recognition

1. Donghong Ji
2. Xindong Wu
3. Shengqiong Wu
4. Fei Li
5. Shirui Pan
6. Meishan Zhang
7. Yufei Wang
8. Hao Fei

Citations in the corpus

• Unifying Large Language Models and Knowledge Graphs: A Roadmap (2023, methodology): “CDML [156] proposes a cross document language modeling method which pre-trains a Long-former [214] encoder on concatenated related documents and employs an MLP for binary classification to determine whether a pair of mentions is coreferent or not.”
• Unified Named Entity Recognition as Word-Word Relation Classification (2021, methodology): “…(Wang et al. 2020; Yu et al. 2020; Shen et al. 2021), hypergraph-based (Wang and Lu 2018) and sequence-to-sequence (Strakov ´ a et al. 2019; Yan et al. 2021) approaches, and achieves the SoTA performances on F1 scores, with 87.52%, 86.79% and 81.39% on ACE2004, ACE2005 and GENIA,…”