HIT: Nested Named Entity Recognition via Head-Tail Pair and Token Interaction

Named entity recognition (NER) is a wellstudied task in natural language processing. Traditional NER research only deals with flat entities and ignores nested entities. The span-based methods treat entity recognition as a span classification task. Although these methods have the innate ability to handle nested NER, they suffer from high computational cost, ignorance of boundary information, under-utilization of the spans that partially match with entities, and difficulties in long entity recognition. To tackle these issues, we propose a two-stage entity identifier. First we generate span proposals by filtering and boundary regression on the seed spans to locate the entities, and then label the boundaryadjusted span proposals with the corresponding categories. Our method effectively utilizes the boundary information of entities and partially matched spans during training. Through boundary regression, entities of any length can be covered theoretically, which improves the ability to recognize long entities. In addition, many low-quality seed spans are filtered out in the first stage, which reduces the time complexity of inference. Experiments on nested NER datasets demonstrate that our proposed method outperforms previous state-of-the-art models.

show abstract

“…• HIT (Wang et al, 2020b) leverages the headtail pair and token interaction to express the nested entities.…”

Section: A2 Baseline Methodsmentioning

confidence: 99%

Locate and Label: A Two-stage Identifier for Nested Named Entity Recognition

Shen¹,

Ma²,

Tan³

et al. 2021

Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Confer

109

View full text Add to dashboard Cite

show abstract

“…Finkel and Manning (2009) regarded the parsing nodes as a span. Xu et al (2017); Luan et al (2019); Yamada et al (2020); Li et al (2020b); Yu et al (2020); Wang et al (2020a) tried to enumerate all spans. Following Lu and Roth (2015), hypergraph methods which can effectively represent exponentially many possible nested mentions in a sentence have been extensively studied in the NER tasks (Katiyar and Cardie, 2018;Wang and Lu, 2018;Muis and Lu, 2016).…”

Section: Ner Subtasksmentioning

confidence: 99%

“…Combined token-level and span-level classification To avoid enumerating all possible spans and incorporate the entity boundary information into the model, Wang and Lu (2019); ; Lin et al (2019); Wang et al (2020b); Luo and Zhao (2020) proposed combining the tokenlevel classification and span-level classification.…”

Section: Ner Subtasksmentioning

confidence: 99%

“…Inspired by sequence labelling's success in the flat NER subtask, Metke-Jimenez and Karimi (2016); Muis and Lu (2017) tried to formulate the nested and discontinuous NER into the sequence labelling problem. 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. Another way to efficiently represent spans is to use the hypergraph (Lu and Roth, 2015;Katiyar and Cardie, 2018;Wang and Lu, 2018;Muis and Lu, 2016).…”

Section: Introductionmentioning

confidence: 99%

“…One tagging schema can hardly fit for all three NER subtasks 2 (Ratinov and Roth, 2009;Metke-Jimenez and Karimi, 2016;Straková et al, 2019;. While the span-based models need to enumerate all possible spans, which is quadratic to the length of the sentence and is almost impossible to enumerate in the discontinuous NER scenario (Yu et al, 2020). Therefore, span-based methods usually will set a maximum span length (Xu et al, 2017;Luan et al, 2019;Wang and Lu, 2018).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Unified Generative Framework for Various NER Subtasks

Yan

Gui

Dai

et al. 2021

Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Confer

130

View full text Add to dashboard Cite

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-theart (SoTA) or near SoTA performance on eight English NER datasets, including two flat NER datasets, three nested NER datasets, and three discontinuous NER datasets 1 .

show abstract