Document-Level Named Entity Recognition by Incorporating Global and Neighbor Features

Hu, Anwen; Dou, Zhicheng; Wen, Ji-Rong

doi:10.1007/978-3-030-31624-2_7

Cited by 2 publications

(3 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Document-level Tagging Document-level tagging introduced more contextual features to improve the performance of tagging. Some early works introduced non-local information (Finkel et al, 2005;Krishnan and Manning, 2006) (Hu et al, 2020(Hu et al, , 2019, chemical NER (Luo et al, 2018), disease NER , and Chinese patent Xue, 2014, 2016). Compared with these works, instead of proposing a novel model, we focus on investigating when and why the larger-context training, as a general strategy, can work.…”

Section: Related Workmentioning

confidence: 99%

“…Naturally, it would be interesting to see what if larger-context information (e.g., taking information of neighbor sentences into account) is introduced to modern top-scoring systems, which have shown superior performance under the sentencelevel setting. A small number of works have made seminal exploration in this direction, in which part of works show significant improvement of largercontext (Luo et al, 2020; while others don't (Hu et al, 2020(Hu et al, , 2019Luo et al, 2018). Therefore, it's still unclear when and why largercontext training is beneficial for tagging tasks.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Larger-Context Tagging: When and Why Does It Work?

Fu¹,

Feng²,

Zhang³

et al. 2021

Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Langua

View full text Add to dashboard Cite

The development of neural networks and pretraining techniques has spawned many sentence-level tagging systems that achieved superior performance on typical benchmarks. However, a relatively less discussed topic is what if more context information is introduced into current top-scoring tagging systems. Although several existing works have attempted to shift tagging systems from sentence-level to document-level, there is still no consensus conclusion about when and why it works, which limits the applicability of the larger-context approach in tagging tasks. In this paper, instead of pursuing a state-of-the-art tagging system by architectural exploration, we focus on investigating when and why the larger-context training, as a general strategy, can work.To this end, we conduct a thorough comparative study on four proposed aggregators for context information collecting and present an attribute-aided evaluation method to interpret the improvement brought by largercontext training. Experimentally, we set up a testbed based on four tagging tasks and thirteen datasets. Hopefully, our preliminary observations can deepen the understanding of larger-context training and enlighten more follow-up works on the use of contextual information.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Larger-Context Tagging: When and Why Does It Work?

Fu¹,

Feng²,

Zhang³

et al. 2021

Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Langua

View full text Add to dashboard Cite

show abstract

“…Luo et al (2020) proposed to use a memory network to record the document-aware information. Besides, document-level features was introduced by different domains to alleviate label inconsistency problems, such as news NER (Hu et al, 2020(Hu et al, , 2019, chemical NER (Luo et al, 2018), disease NER , and Chinese patent Xue, 2014, 2016). Compared with these works, instead of proposing a novel model, we focus on investigating when and why the larger-context training, as a general strategy, can work.…”

Section: Related Workmentioning

confidence: 99%

Larger-Context Tagging: When and Why Does It Work?

Feng²,

Zhang

et al. 2021

Preprint

View full text Add to dashboard Cite

The development of neural networks and pretraining techniques has spawned many sentence-level tagging systems that achieved superior performance on typical benchmarks. However, a relatively less discussed topic is what if more context information is introduced into current top-scoring tagging systems. Although several existing works have attempted to shift tagging systems from sentence-level to document-level, there is still no consensus conclusion about when and why it works, which limits the applicability of the larger-context approach in tagging tasks. In this paper, instead of pursuing a state-of-the-art tagging system by architectural exploration, we focus on investigating when and why the larger-context training, as a general strategy, can work.To this end, we conduct a thorough comparative study on four proposed aggregators for context information collecting and present an attribute-aided evaluation method to interpret the improvement brought by larger-context training. Experimentally, we set up a testbed based on four tagging tasks and thirteen datasets. Hopefully, our preliminary observations can deepen the understanding of largercontext training and enlighten more follow-up works on the use of contextual information. We have released all relevant codes for future researchers to run similar analyses: https: //github.com/jlfu/larger-context.

show abstract

Document-Level Named Entity Recognition by Incorporating Global and Neighbor Features

Cited by 2 publications

References 15 publications

Larger-Context Tagging: When and Why Does It Work?

Larger-Context Tagging: When and Why Does It Work?

Larger-Context Tagging: When and Why Does It Work?

Contact Info

Product

Resources

About