KINNEWS and KIRNEWS: Benchmarking Cross-Lingual Text Classification for Kinyarwanda and Kirundi

Proceedings of the 28th International Conference on Computational Linguistics, pages 5507–5521 Barcelona, Spain (Online), December 8-13, 2020 5507 KINNEWS and KIRNEWS: Benchmarking Cross-Lingual Text Classification for Kinyarwanda and Kirundi Rubungo Andre Niyongabo1,2 and Hong Qu1,∗and Julia Kreutzer2 and Li Huang1 1School of Computer Science and Engineering, Computational Intelligence Lab, University of Electronic Science and Technology of China, China 2Masakhane, Africa niyongabor.andre@std.uestc.edu.cn, hongqu@uestc.edu.cn, juliakreutzer.jul@gmail.com, lihuang@std.uestc.edu.cn Abstract Recent progress in text classification has been focused on high-resource languages such as En- glish and Chinese. For low-resource languages, amongst them most African languages, the lack of well-annotated data and effective preprocessing, is hindering the progress and the transfer of successful methods. In this paper, we introduce two news datasets (KINNEWS and KIRNEWS) for multi-class classification of news articles in Kinyarwanda and Kirundi, two low-resource African languages. The two languages are mutually intelligible, but while Kinyarwanda has been studied in Natural Language Processing (NLP) to some extent, this work constitutes the first study on Kirundi. Along with the datasets, we provide statistics, guidelines for preprocessing, and monolingual and cross-lingual baseline models. Our experiments show that training em- beddings on the relatively higher-resourced Kinyarwanda yields successful cross-lingual transfer to Kirundi. In addition, the design of the created datasets allows for a wider use in NLP be- yond text classification in future studies, such as representation learning, cross-lingual learning with more distant languages, or as base for new annotations for tasks such as parsing, POS tag- ging, and NER. The datasets, stopwords, and pre-trained embeddings are publicly available at https://github.com/Andrews2017/KINNEWS-and-KIRNEWS-Corpus. 1 Introduction The availability of large monolingual and labeled corpora, paired with innovations in neural text process- ing have led to a rapid improvement of the quality of text classification over the last years.1 However, the effectiveness of deep-learning-based text classification models depends on the amount of monolin- gual and labeled data. Low-resource languages are traditionally left behind because of the few available prepared resources for these languages to extract the data from (Joshi et al., 2020). However, nowadays, the increase in internet use in many African developing countries has made access to information easier. This in turn has strengthened the news agencies of those countries to cover many stories in their native languages. For example, BBC News now provides online news in Arabic, Amharic, Hausa, Kiswahili, Somali, Oromo, Igbo, Nigerian Pidgin, Tigrigna, Kinyarwanda and Kirundi.2 This development makes news the most reliable source of data for low-resource languages. We explore this opportunity for the example of Kinyarwanda and Kirundi, two African low-resource Bantu languages, and build news clas- sification benchmarks from online news articles. This has the goal to enable NLP researchers to include Kinyarwanda and Kirundi in the evaluation of novel text classification approaches, and diversify the current NLP landscape. Kinyarwanda is one of the official languages of Rwanda3 and belongs to the Niger-Congo language family. According to The New Times,4 it is spoken by approximately 30 million people from four dif- ∗Corresponding author This work is licensed under a Creative Commons Attribution 4.0 …

Content truncated to 500 words