Abstract
We revisit the idea of mining Wikipedia in order to generate named-entity annotations. We propose a new methodology that we applied to English Wikipedia to build WiNER, a large, high quality, annotated corpus. We evaluate its usefulness on 6 NER tasks, comparing 4 popular state-of-the art approaches. We show that LSTM-CRF is the approach that benefits the most from our corpus. We report impressive gains with this model when using a small portion of WiNER on top of the CONLL training material. Last, we propose a simple but efficient method for exploiting the full range of WiNER, leading to further improvements.- Anthology ID:
- I17-1042
- Volume:
- Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
- Month:
- November
- Year:
- 2017
- Address:
- Taipei, Taiwan
- Venue:
- IJCNLP
- SIG:
- Publisher:
- Asian Federation of Natural Language Processing
- Note:
- Pages:
- 413–422
- Language:
- URL:
- https://aclanthology.org/I17-1042
- DOI:
- Cite (ACL):
- Abbas Ghaddar and Phillippe Langlais. 2017. WiNER: A Wikipedia Annotated Corpus for Named Entity Recognition. In Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 413–422, Taipei, Taiwan. Asian Federation of Natural Language Processing.
- Cite (Informal):
- WiNER: A Wikipedia Annotated Corpus for Named Entity Recognition (Ghaddar & Langlais, IJCNLP 2017)
- PDF:
- https://preview.aclanthology.org/paclic-22-ingestion/I17-1042.pdf