Example-Based Named Entity Recognition

By Morteza Ziyadi, Yuting Sun, Abhishek Goswami, Jade Huang, Weizhu Chen. 2020

36 citations recorded by the source corpus.

We present a novel approach to named entity recognition (NER) in the presence of scarce data that we call example-based NER. Our train-free few-shot learning approach takes inspiration from question-answering to identify entity spans in a new and unseen domain. In comparison with the current state-of-the-art, the proposed method performs significantly better, especially when using a low number of support examples.

Subfields: Artificial Intelligence, Natural Language Processing, 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

1. Jianfeng Gao
2. Chunyuan Li
3. Lawrence Carin
4. Yizhe Zhang
5. Weizhu Chen
6. Dinghan Shen
7. Jiawei Han
8. Zhe Gan

In Natural Language Processing

1. Jianfeng Gao
2. Chunyuan Li
3. Lawrence Carin
4. Weizhu Chen
5. Yizhe Zhang
6. Yue Zhang
7. Dinghan Shen
8. Baolin Peng

In Information Extraction

1. Jianfeng Gao
2. Yue Zhang
3. Yoav Goldberg

Citations in the corpus

• What Makes Good In-Context Examples for GPT-3? (2021, background): “It is very related to the exemplar-based learning (J¨akel et al., 2008; Ziyadi et al., 2020).”
• Few-Shot Named Entity Recognition: A Comprehensive Study (2020, methodology): “Our work is similar to (Ziyadi et al., 2020; Wiseman and Stratos, 2019) in that all of them utilize the nearest neighbor criterion to assign the entity type, but differs in that (Ziyadi et al., 2020; Wiseman and Stratos, 2019) consider every individual token instance for nearest neighbor…”
• Template-Based Named Entity Recognition Using BART (2021, methodology): “For example, when there are only 10 training instances, the method of Ziyadi et al. (2020) gives a F1 score of 40.1% on MIT Movie, as compared to 28.3% by BERT, despite that BERT requires re-training with a different output layer on both CoNLL03 and MIT Movie.”