تقرير
MasakhaNER 2.0: Africa-centric Transfer Learning for Named Entity Recognition
العنوان: | MasakhaNER 2.0: Africa-centric Transfer Learning for Named Entity Recognition |
---|---|
المؤلفون: | Adelani, David Ifeoluwa, Neubig, Graham, Ruder, Sebastian, Rijhwani, Shruti, Beukman, Michael, Palen-Michel, Chester, Lignos, Constantine, Alabi, Jesujoba O., Muhammad, Shamsuddeen H., Nabende, Peter, Dione, Cheikh M. Bamba, Bukula, Andiswa, Mabuya, Rooweither, Dossou, Bonaventure F. P., Sibanda, Blessing, Buzaaba, Happy, Mukiibi, Jonathan, Kalipe, Godson, Mbaye, Derguene, Taylor, Amelia, Kabore, Fatoumata, Emezue, Chris Chinenye, Aremu, Anuoluwapo, Ogayo, Perez, Gitau, Catherine, Munkoh-Buabeng, Edwin, Koagne, Victoire M., Tapo, Allahsera Auguste, Macucwa, Tebogo, Marivate, Vukosi, Mboning, Elvis, Gwadabe, Tajuddeen, Adewumi, Tosin, Ahia, Orevaoghene, Nakatumba-Nabende, Joyce, Mokono, Neo L., Ezeani, Ignatius, Chukwuneke, Chiamaka, Adeyemi, Mofetoluwa, Hacheme, Gilles Q., Abdulmumin, Idris, Ogundepo, Odunayo, Yousuf, Oreen, Ngoli, Tatiana Moteu, Klakow, Dietrich |
سنة النشر: | 2022 |
المجموعة: | Computer Science |
مصطلحات موضوعية: | Computer Science - Computation and Language |
الوصف: | African languages are spoken by over a billion people, but are underrepresented in NLP research and development. The challenges impeding progress include the limited availability of annotated datasets, as well as a lack of understanding of the settings where current methods are effective. In this paper, we make progress towards solutions for these challenges, focusing on the task of named entity recognition (NER). We create the largest human-annotated NER dataset for 20 African languages, and we study the behavior of state-of-the-art cross-lingual transfer methods in an Africa-centric setting, demonstrating that the choice of source language significantly affects performance. We show that choosing the best transfer language improves zero-shot F1 scores by an average of 14 points across 20 languages compared to using English. Our results highlight the need for benchmark datasets and models that cover typologically-diverse African languages. Comment: Accepted to EMNLP 2022 (updated Github link) |
نوع الوثيقة: | Working Paper |
URL الوصول: | http://arxiv.org/abs/2210.12391 |
رقم الأكسشن: | edsarx.2210.12391 |
قاعدة البيانات: | arXiv |
الوصف غير متاح. |