FLAT: Chinese NER Using Flat-Lattice Transformer

By Xiaonan Li, Hang Yan, Xipeng Qiu, Xuanjing Huang. Annual Meeting of the Association for Computational Linguistics, 2020

451 citations recorded by the source corpus.

Recently, the character-word lattice structure has been proved to be effective for Chinese named entity recognition (NER) by incorporating the word information. However, since the lattice structure is complex and dynamic, the lattice-based models are hard to fully utilize the parallel computation of GPUs and usually have a low inference speed. In this paper, we propose FLAT: Flat-LAttice Transformer for Chinese NER, which converts the lattice structure into a flat structure consisting of spans. Each span corresponds to a character or latent word and its position in the original lattice. With the power of Transformer and well-designed position encoding, FLAT can fully leverage the lattice information and has an excellent parallel ability. Experiments on four datasets show FLAT outperforms other lexicon-based models in performance and efficiency.

Subfields: Artificial Intelligence, Management Science and Operations Research

View Paper: https://www.semanticscholar.org/paper/7066df8fd89cca546d1ef3d66679cb15eba48d50

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. Xipeng Qiu
2. Hang Yan
3. Zheng Zhang
4. Qipeng Guo
5. Tianyang Lin
6. Yuxin Wang
7. Xiangyang Liu
8. Donghong Ji

In Management Science and Operations Research

1. Xipeng Qiu
2. Hang Yan
3. Donghong Ji
4. Fei Li
5. Zheng Zhang
6. Meishan Zhang
7. Qipeng Guo

Citations in the corpus

• A Unified Generative Framework for Various NER Subtasks (2021, methodology): “…labelling formulation, which will assign a tag to each token in the sentence, has been widely used in the flat NER field (McCal-lum and Li, 2003; Collobert et al., 2011; Huang et al., 2015; Chiu and Nichols, 2016; Lample et al., 2016; Strakov´a et al., 2019; Yan et al., 2019; Li et al., 2020a).”
• A Survey of Transformers (2021, background): “, machine translation [35, 91, 104, 122, 136], language modeling [24, 103, 110, 121] and named entity recognition [80, 153].”
• Unified Named Entity Recognition as Word-Word Relation Classification (2021, methodology): “Current mainstream work combine the CRF (Lafferty et al. 2001; Finkel et al. 2005) with neural architecture, such as CNN (Collobert et al. 2011; Strubell et al. 2017), bi-directional LSTM (Huang et al. 2015; Lample et al. 2016), and Trans-former (Yan et al. 2019; Li et al. 2020b).”