Introduction to the CoNLL-2002 Shared Task: Language-Independent Named Entity Recognition
By E. Tjong Kim Sang. 2002
861 citations recorded by the source corpus.
We describe the CoNLL-2002 shared task: language-independent named entity recognition. We give background information on the data sets and the evaluation method, present a general overview of the systems that have taken part in the task and discuss their performance.
Subfields: Artificial Intelligence, Evaluation & Benchmarks, Information Extraction
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
- Luke S. Zettlemoyer
- Mohit Bansal
- Graham Neubig
- Noah A. Smith
- Jianfeng Gao
- Percy Liang
- Furu Wei
- Yejin Choi
In Evaluation & Benchmarks
- Luke S. Zettlemoyer
- Noah A. Smith
- Mark Dredze
- Alexis Conneau
- Shijie Wu
- Edouard Grave
- Pengfei Liu
- André F. T. Martins
In Information Extraction
- Pengfei Liu
- Jinlan Fu
- André F. T. Martins
- Afshin Rahimi
- Julia Kreutzer
- Mark Dredze
- Vikas Yadav
- Steven Bethard
Citations in the corpus
- Unsupervised Cross-lingual Representation Learning at Scale (2019, methodology): “We consider the LSTM + CRF approach from Lample et al. (2016) and the Flair model from Akbik et al. (2018) CoNLL-2002 and CoNLL-2003 (F1 score).”
- Introduction to the CoNLL-2003 Shared Task: Language-Independent Named Entity Recognition (2003, background): “The shared task of CoNLL-2002 dealt with named entity recognition for Spanish and Dutch (Tjong Kim Sang, 2002).”
- How Multilingual is Multilingual BERT? (2019, methodology): “We perform NER experiments on two datasets: the publicly available CoNLL-2002 and -2003 sets, containing Dutch, Spanish, English, and German (Tjong Kim Sang, 2002; Sang and Meulder, 2003); and an in-house dataset with 16 languages, 2 using the same CoNLL categories.”
- Beto, Bentz, Becas: The Surprising Cross-Lingual Effectiveness of BERT (2019, methodology): “3 Named Entity Recognition We use the CoNLL 2002 and 2003 NER shared tasks (Sang, 2002; Sang and Meulder, 2003) which total 4 languages.”
- Stanza: A Python Natural Language Processing Toolkit for Many Human Languages (2020, methodology): “For NER, we train and evaluate Sta n z a with 12 publicly available datasets covering 8 major languages as shown in Table 3 (Nothman et al., 2013; Tjong Kim Sang and De Meulder, 2003; Tjong Kim Sang, 2002; Benikova et al., 2014; Mohit et al., 2012; Taulé et al., 2008; Weischedel et al., 2013).”
- Exploring Fine-tuning Techniques for Pre-trained Cross-lingual Models via Continual Learning (2020, methodology): “For the cross-lingual NER task, we utilize CoNLL 2002 (Tjong Kim Sang, 2002) and CoNLL 2003 (Sang and De Meulder, 2003), which contain English (en), German (de), Spanish (es) and Dutch (nl) to evaluate our approaches.”
- Improving Named Entity Recognition by External Context Retrieving and Cooperative Learning (2021, background): “…et al., 2020) utilizes the strength of pretrained contextual embeddings over long-range dependency and encodes the document-level contexts for token representations to achieve state-of-the-art accuracy on CoNLL 2002/2003 NER datasets (Tjong Kim Sang, 2002; Tjong Kim Sang and De Meulder, 2003).”
- SpanNER: Named Entity Re-/Recognition as Span Prediction (2021, methodology): “CoNLL-2002 3 (Sang, 2002) contains annotated corpus in Dutch (NL) collected from De Morgen news, and Spanish (ES) collected from Spanish EFE News Agency.”
- Fine-Grained Analysis of Propaganda in News Article (2019, background): “…is comparable to standard datasets for other fine-grained text analysis tasks, such as named entity recognition, e.g., CoNLL’02 and CoNLL’03 covered 381K, 333K, 310K, and 301K tokens for Spanish, Dutch, German, and English, respectively (Tjong Kim Sang, 2002; Tjong Kim Sang and De Meul-der, 2003).”
- Learning What’s Easy: Fully Differentiable Neural Easy-First Taggers (2017, methodology): “We used the official datasets from the CoNLL 2002-3 shared tasks (Sang, 2002; Sang and De Meulder, 2003), which tag names, locations, and organizations using a BIO scheme, and cover four languages (Dutch, English, German, and Spanish).”
- Results of the WNUT2017 Shared Task on Novel and Emerging Entity Recognition (2017, methodology): “Named entity recognition has a long standing tradition of shared tasks, with the most prominent being the multilingual named entity recognition tasks organized at CoNLL in 2002 and 2003 (Sang, 2002; Tjong Kim Sang and Meulder, 2003).”
- ChatGPT Beyond English: Towards a Comprehensive Evaluation of Large Language Models in Multilingual Learning (2023, background): “Named Entity Recognition (NER) is an important task in NLP (Sang and Meulder, 2002), aiming to identify spans and semantic types of names (e.g., person, organization) in text.”
- Spanish Pre-trained BERT Model and Evaluation Data (2023, methodology): “Since one of the goals of our work was to compare the performance of Spanish-BERT to mBERT (Wu & Dredze, 2019; Yang et al., 2019a), our experimental setup closely follows the one by Wu & Dredze (2019). Task specific output layers are incorporated, following the original BERT work (Devlin et al.”