A Span-Based Model for Joint Overlapped and Discontinuous Named Entity Recognition

Li, Fēi; Lin, Zhichao; Zhang, Meishan; Ji, Donghong

doi:10.18653/v1/2021.acl-long.372

Cited by 69 publications

(43 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recent years, a body of literature emerged on span-based models, which were compatible with both flat and nested entities, and achieved SOTA performance (Eberts and Ulges, 2020;Yu et al, 2020;Li et al, 2021). These models typically enumerate all possible candidate text spans and then classify each span into entity types.…”

Section: Related Workmentioning

confidence: 99%

“…2 In addition, some studies have also reported that incorrect boundary is a major source of entity recognition error Eberts and Ulges, 2020). Recently, span-based models have gained much popularity in NER studies, and achieved state-ofthe-art (SOTA) results (Eberts and Ulges, 2020;Yu et al, 2020;Li et al, 2021). This approach typically enumerates all candidate spans and classifies them into entity types (including a "non-entity" type); the annotated spans are scarce and assigned with full probability to be an entity, whereas all other spans are assigned with zero probability.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Boundary Smoothing for Named Entity Recognition

Zhu¹,

Li²

2022

Preprint

View full text Add to dashboard Cite

Neural named entity recognition (NER) models may easily encounter the over-confidence issue, which degrades the performance and calibration. Inspired by label smoothing and driven by the ambiguity of boundary annotation in NER engineering, we propose boundary smoothing as a regularization technique for span-based neural NER models. It re-assigns entity probabilities from annotated spans to the surrounding ones. Built on a simple but strong baseline, our model achieves results better than or competitive with previous stateof-the-art systems on eight well-known NER benchmarks. 1 Further empirical analysis suggests that boundary smoothing effectively mitigates over-confidence, improves model calibration, and brings flatter neural minima and more smoothed loss landscapes.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Boundary Smoothing for Named Entity Recognition

Zhu¹,

Li²

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Fisher and Vlachos (2019) proposed a neural network that merges NEs or tokens to generate nested structure and labels them. Several recent researches applied multi-layer GCN to accomplish nested NER (Li et al, 2021;Luo and Zhao, 2020). These are practical methods, nonetheless, the existing models with a huge depth are computationally impractical.…”

Section: Related Workmentioning

confidence: 99%

Nested Named Entity Recognition as Holistic Structure Parsing

Yang¹,

Li²,

Zhang³

2022

Preprint

View full text Add to dashboard Cite

As a fundamental natural language processing task and one of core knowledge extraction techniques, named entity recognition (NER) is widely used to extract information from texts for downstream tasks. Nested NER is a branch of NER in which the named entities (NEs) are nested with each other. However, most of the previous studies on nested NER usually apply linear structure to model the nested NEs which are actually accommodated in a hierarchical structure. Thus in order to address this mismatch, this work models the full nested NEs in a sentence as a holistic structure, then we propose a holistic structure parsing algorithm to disclose the entire NEs once for all. Besides, there is no research on applying corpus-level information to NER currently. To make up for the loss of this information, we introduce Point-wise Mutual Information (PMI) and other frequency features from corpus-aware statistics for even better performance by holistic modeling from sentence-level to corpus-level. Experiments show that our model yields promising results on widely-used benchmarks which approach or even achieve state-of-the-art. Further empirical studies show that our proposed corpusaware features can substantially improve NER domain adaptation, which demonstrates the surprising advantage of our proposed corpuslevel holistic structure modeling.

show abstract

“…Team Abrosimov_Kirll (Saldon) used the span-based Sodner model (Li et al, 2021) that can recognize both overlapped and discontinuous entities jointly. The model is based on the graph convolutional network architecture.…”

Section: Participants' Submissionsmentioning

confidence: 99%

RuNNE-2022 Shared Task: Recognizing Nested Named Entities

Artemova¹,

Zmeev²,

Loukachevitch³

et al. 2022

Preprint

View full text Add to dashboard Cite

The RuNNE Shared Task approaches the problem of nested named entity recognition. The annotation schema is designed in such a way, that an entity may partially overlap or even be nested into another entity. This way, the named entity "The Yermolova Theatre" of type ORGANIZATION houses another entity "Yermolova" of type PERSON. We adopt the Russian NEREL dataset (Loukachevitch et al., 2021) for the RuNNE Shared Task. NEREL comprises news texts written in the Russian language and collected from the Wikinews portal. The annotation schema includes 29 entity types. The nestedness of named entities in NEREL reaches up to six levels. The RuNNE Shared Task explores two setups. (i) In the general setup all entities occur more or less with the same frequency. (ii) In the few-shot setup the majority of entity types occur often in the training set. However, some of the entity types are have lower frequency, being thus challenging to recognize. In the test set the frequency of all entity types is even.This paper reports on the results of the RuNNE Shared Task. Overall the shared task has received 156 submissions from nine teams. Half of the submissions outperform a straightforward BERT-based baseline in both setups. This paper overviews the shared task setup and discusses the submitted systems, discovering meaning insights for the problem of nested NER. The links to the evaluation platform and the data from the shared task are available in our github repository.

show abstract

A Span-Based Model for Joint Overlapped and Discontinuous Named Entity Recognition

Cited by 69 publications

References 50 publications

Boundary Smoothing for Named Entity Recognition

Boundary Smoothing for Named Entity Recognition

Nested Named Entity Recognition as Holistic Structure Parsing

RuNNE-2022 Shared Task: Recognizing Nested Named Entities

Contact Info

Product

Resources

About