Named Entity Recognition as Dependency Parsing

By Juntao Yu, Bernd Bohnet, Massimo Poesio. Annual Meeting of the Association for Computational Linguistics, 2020

501 citations recorded by the source corpus.

Named Entity Recognition (NER) is a fundamental task in Natural Language Processing, concerned with identifying spans of text expressing references to entities. NER research is often focused on flat entities only (flat NER), ignoring the fact that entity references can be nested, as in [Bank of [China]] (Finkel and Manning, 2009). In this paper, we use ideas from graph-based dependency parsing to provide our model a global view on the input via a biaffine model (Dozat and Manning, 2017). The biaffine model scores pairs of start and end tokens in a sentence which we use to explore all spans, so that the model is able to predict named entities accurately. We show that the model works well for both nested and flat NER through evaluation on 8 corpora and achieving SoTA performance on all of them, with accuracy gains of up to 2.2 percentage points.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/fe5bec4083e00764146df9f0191790cc72d972b9

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. Pengfei Liu
3. Xuanjing Huang
4. Jie Tang
5. Zheng Zhang
6. Xiao Liu
7. Shirui Pan
8. Jinlan Fu

Citations in the corpus

• A large language model for electronic health records (2022, background): “16 In the general domain, the transformer-based NLP models have achieved state-of-the-art performance for name entity recognition 17–19 , relation extraction 20–24 , sentence similarity 25–27 , natural language inference 27–30 , and question answering 27,28,31,32 .”
• Unifying Large Language Models and Knowledge Graphs: A Roadmap (2023, methodology): “The span-based method [190]–[194] is a popular branch of nested NER which involves enumerating all candidate spans and classifying them into entity types (including a non-entity type).”
• Unified Named Entity Recognition as Word-Word Relation Classification (2021, methodology): “For ACE2004 and ACE2005 corpora in Chinese, we reproduce the SoTA models proposed by Yu et al. (2020) and Shen et al. (2021), and list their results in Table 5.”
• Improving Named Entity Recognition by External Context Retrieving and Cooperative Learning (2021, background): “Recent work (Devlin et al., 2019; Yu et al., 2020; Yamada et al., 2020) found that including document-level contexts of the target sentence in the input of contextual embeddings meth-ods can further boost the accuracy of NER models. senate democrats eliminated the nuclear option when they had the…”
• SpanNER: Named Entity Re-/Recognition as Span Prediction (2021, methodology): “…al., 2020; Fu et al., 2021), to span-level prediction (S PAN N ER ) (Li et al., 2020; Mengge et al., 2020; Jiang et al., 2020; Ouchi et al., 2020; Yu et al., 2020), which regards NER either as question answering (Li et al., 2020; Mengge et al., 2020), span classification (Jiang et al., 2020;…”
• A Unified Generative Framework for Various NER Subtasks (2021, methodology): “For the nested and discontinuous NER subtasks, instead of assigning labels to each token directly, Xu et al. (2017); Wang and Lu (2019); Yu et al. (2020); Li et al. (2020b) tried to enumerate all possible spans and conduct the span-level classification.”
• DeepStruct: Pretraining of Language Models for Structure Prediction (2022, methodology): “Comparison Methods We compare our method D EEP S TRUCT on the four datasets to the following NER methods: (i) BERT-MRC (Li et al., 2020a): this method formulates NER as a machine reading comprehension problem, (ii) BERT-MRC+DSC (Li et al., 2020b): this model is a dice-loss enhanced version of BERT-M”
• Evaluating the carbon footprint of NLP methods: a survey and analysis of existing tools (2021, unknown): “Measuring carbon footprint is a novel under-taking Table 1 shows that the availability of tools (Yu et al., 2020) while the bottom part presents the results obtained with an implementation of the method by (Ma and Hovy, 2016).”