A survey of named entity recognition and classification

By David Nadeau, Satoshi Sekine. 2007

2,979 citations recorded by the source corpus.

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

Citations in the corpus

Recurrent Neural Networks for Classifying Relations in Clinical Notes (2017, neutral): “State-of-the-art named entity recognizers can now recognize concept with high accuracy [1], but relation extraction is not as straightforward.”
End-to-End Relation Extraction using LSTMs on Sequences and Tree Structures (2016, background): “Recently, Huang et al. (2015) showed that building a conditional random ﬁeld (CRF) layer on top of bidirectional LSTM-RNNs performs comparably to the state-of-the-art methods in the part-of-speech (POS) tagging, chunking, and NER.”
Dice Loss for Data-imbalanced NLP Tasks (2019, background): “Table 1 gives concrete examples: for the Named Entity Recognition (NER) task (Sang and De Meulder, 2003; Nadeau and Sekine, 2007), most tokens are backgrounds with tagging class O .”
Label Noise Reduction in Entity Typing by Heterogeneous Partial-Label Embedding (2016, background): “Traditional named entity recognition systems [16] focus on coarse types ( e.g. , person , location ) and cast the problem as multi-class classiﬁcation following the type mu-0 tual exclusion assumption ( i.e. , one type per mention) [18].”
A Survey on Deep Learning for Named Entity Recognition (2018, methodology): “A typical approach of unsupervised learning is clustering [1].”
Going out on a limb: Joint Extraction of Entity Mentions and Relations without Dependency Trees (2017, background): “These can be broadly categorized into – 1) pipeline models that treat the identification of entity mentions (Nadeau and Sekine, 2007) and relation classification (Zhou et al., 2005) as two separate tasks; and 2) joint models, also the more recent, which simultaneously identify the entity mention…”
Bridging semantics and syntax with graph algorithms - state-of-the-art of extracting biomedical relations (2017, background): “State-of-the-art named entity recognizers can automatically annotate text with high accuracy [1, 2], but relation extraction is not as straightforward.”
Bridging semantics and syntax with graph algorithms —state-of-the-art of extracting biomedical relations (2015, background): “State-of-the-art named entity recognizers can automatically annotate text with high accuracy [1,2], but relation extraction is not as straightforward.”
Analyzing Leakage of Personally Identifiable Information in Language Models (2023, methodology): “When datasets are large, it is necessary to rely on Named Entity Recognition (NER) [47].”
FedNER: Privacy-preserving Medical Named Entity Recognition with Federated Learning (2020, methodology): “Both rule-based methods and statistical methods are proposed to tackle NER in the medical domain (Dong et al., 2016; Nadeau and Sekine, 2007).”
Natural Language Processing for EHR-Based Pharmacovigilance: A Structured Review (2017, background): “NER has been extensively studied both in the general NLP [45] and the biomedical NLP domains [46].”
CoType: Joint Extraction of Typed Entities and Relations with Knowledge Bases (2016, background): “Most existing work follows an incremental diagram—they first perform entity recognition and typing [34, 40] to extract typed entity mentions, and then solve relation extraction [2, 17] to identify relation mentions of target types.”
A Survey on Recent Advances in Named Entity Recognition from Deep Learning models (2018, methodology): “These systems were followed by NER systems based on feature-engineering and machine learning (Nadeau and Sekine, 2007).”
Unsupervised Grounding of Plannable First-Order Logic Representation from Images (2019, background): “Object recognition in computer vision (Redmon et al. 2016, YOLO) or named entity (noun / “objects”) recognition (Nadeau and Sekine 2007; Mohit 2014) in Natural Language Processing, are both becoming increasingly successful.”
Few-Shot Named Entity Recognition: A Comprehensive Study (2020, background): “, 2019) and other language understanding applications (Nadeau and Sekine, 2007; Shaalan, 2014).”
IXA pipeline: Efficient and Ready to Use Multilingual NLP tools (2014, background): “Most of the Named Entity Recognition and Classiﬁcation (NERC) systems nowdays consist of language independent systems (sometimes enriched with gazeteers) based on automatic learning of statistical models (Nadeau and Sekine, 2007). ixa-pipe-nerc provides NERC for English and Spanish.”
Recognizing Named Entities in Tweets (2011, background): “Named Entities Recognition (NER) is generally understood as the task of identifying mentions of rigid designators from text belonging to named-entity types such as persons, organizations and locations (Nadeau and Sekine, 2007).”