Despite recent availability of large transcribed Kinyarwanda speech data,
achieving robust speech recognition for Kinyarwanda is still challenging. In
this work, we show that using self-supervised pre-training, following a simple
curriculum schedule during fine-tuning and using semi-supervised learning to
leverage large unlabelled speech data significantly improve speech recognition
performance for Kinyarwanda. Our approach focuses on using public domain data
only. A new studio-quality speech dataset is collected from a public website,
then used to train a clean baseline model. The clean baseline model is then
used to rank examples from a more diverse and noisy public dataset, defining a
simple curriculum training schedule. Finally, we apply semi-supervised learning
to label and learn from large unlabelled data in four successive generations.
Our final model achieves 3.2% word error rate (WER) on the new dataset and
15.9% WER on Mozilla Common Voice benchmark, which is state-of-the-art to the
best of our knowledge. Our experiments also indicate that using syllabic rather
than character-based tokenization results in better speech recognition
performance for Kinyarwanda.

通过自监督预训练、课程表安排进行微调以及利用大规模未标记语音数据的半监督学习，我们展示出在金雅琳达语（Kinyarwanda）的语音识别性能方面的显著提升。我们的方法仅关注使用公共领域数据，在公共网站上收集了一个新的高质量语音数据集，然后用于训练一个干净的基线模型，该模型再用于对来自多样且噪声较大的公共数据集中的示例进行排名，从而定义了一个简单的课程表训练计划。最后，我们采用四代连续的半监督学习方法对大规模未标记数据进行标记和学习。根据我们所知，我们的最终模型在新数据集上的字错率（WER）为 3.2％，在 Mozilla Common Voice 基准上的 WER 为 15.9％，这是目前最先进的。我们的实验还表明，对于金雅琳达语的语音识别性能而言，采用音节而不是字符的分词方法结果更好。

KinSPEAK: 通过半监督学习方法改进基尼亚万达语的语音识别

KinSPEAK: Improving speech recognition for Kinyarwanda via  semi-supervised learning methods

This paper describes the system entered by the author to the SemEval-2023
Task 12: Sentiment analysis for African languages. The system focuses on the
Kinyarwanda language and uses a language-specific model. Kinyarwanda morphology
is modeled in a two tier transformer architecture and the transformer model is
pre-trained on a large text corpus using multi-task masked morphology
prediction. The model is deployed on an experimental platform that allows users
to experiment with the pre-trained language model fine-tuning without the need
to write machine learning code. Our final submission to the shared task
achieves second ranking out of 34 teams in the competition, achieving 72.50%
weighted F1 score. Our analysis of the evaluation results highlights challenges
in achieving high accuracy on the task and identifies areas for improvement.

本文描述了作者参加 SemEval-2023 任务 12 的系统，该系统专注于 Kinyarwanda 语言并使用特定于该语言的模型，使用双层变形金刚体系结构对 Kinyarwanda 语言进行建模，变形金刚模型使用多任务掩码形态预测在大型文本语料库上进行预训练。模型部署在实验平台上，使用户可以在不需要编写机器学习代码的情况下尝试使用预训练的语言模型的微调。我们在比赛中提交的最终结果在 34 支队伍中排名第二，实现了 72.50％的加权 F1 得分。我们对评估结果的分析强调了在完成任务时遇到的挑战，并确定了改进的方向。

KINLP 在 SemEval-2023 第 12 项任务中：基尼亚隆达语推特情感分析

KINLP at SemEval-2023 Task 12: Kinyarwanda Tweet Sentiment Analysis

Recent progress in text classification has been focused on high-resource
languages such as English 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
embeddings 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 beyond 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 tagging, and NER. The datasets, stopwords, and pre-trained embeddings are
publicly available at this https URL .

本文提出了两个用于 Kinyarwanda 和 Kirundi 两种低资源非洲语言新闻文章的多类分类的数据集 (KINNEWS 和 KIRNEWS)，并通过实验展示训练较高资源的 Kinyarwanda 能够成功的进行跨语言转移至 Kirundi。这些数据集除了可以被用于文本分类，还可被用于解决跨语言学习、表示学习、语法分析、词性标注和命名实体识别等自然语言处理问题。