This paper describes Tencent's multilingual machine translation systems for the WMT22 shared task on Large-Scale Machine Translation Evaluation for African Languages. We participated in the $\mathbf{constrained}$ translation track in which only the data and pretrained models provided by the organizer are allowed. The task is challenging due to three problems, including the absence of training data for some to-be-evaluated language pairs, the uneven optimization of language pairs caused by data imbalance, and the curse of multilinguality. To address these problems, we adopt data augmentation, distributionally robust optimization, and language family grouping, respectively, to develop our multilingual neural machine translation (MNMT) models. Our submissions won the $\mathbf{1st\ place}$ on the blind test sets in terms of the automatic evaluation metrics. Codes, models, and detailed competition results are available at https://github.com/wxjiao/WMT2022-Large-Scale-African.
The paper describes the University of Cape Town's submission to the constrained track of the WMT22 Shared Task: Large-Scale Machine Translation Evaluation for African Languages. Our system is a single multilingual translation model that translates between English and 8 South / South East African Languages, as well as between specific pairs of the African languages. We used several techniques suited for low-resource machine translation (MT), including overlap BPE, back-translation, synthetic training data generation, and adding more translation directions during training. Our results show the v…
Technical University of Munich（慕尼黑工业大学）；Mila Quebec AI Institute（米拉魁北克人工智能研究所）；Masakhane；Jacobs University Bremen（不来梅雅各布大学）
In this paper, we focus on the task of multilingual machine translation for African languages and describe our contribution in the 2021 WMT Shared Task: Large-Scale Multilingual Machine Translation. We introduce MMTAfrica, the first many-to-many multilingual translation system for six African languages: Fon (fon), Igbo (ibo), Kinyarwanda (kin), Swahili/Kiswahili (swa), Xhosa (xho), and Yoruba (yor) and two non-African languages: English (eng) and French (fra). For multilingual translation concerning African languages, we introduce a novel backtranslation and reconstruction objective, BT\&REC, …
Building natural language processing systems for non standardized and low resource languages is a difficult challenge. The recent success of large-scale multilingual pretrained language models provides new modeling tools to tackle this. In this work, we study the ability of multilingual language models to process an unseen dialect. We take user generated North-African Arabic as our case study, a resource-poor dialectal variety of Arabic with frequent code-mixing with French and written in Arabizi, a non-standardized transliteration of Arabic to Latin script. Focusing on two tasks, part-of-spee…
University of Trento（特伦托大学）；Fondazione Bruno Kessler（布鲁诺·凯斯勒基金会）
Recent advents in Neural Machine Translation (NMT) have shown improvements in low-resource language (LRL) translation tasks. In this work, we benchmark NMT between English and five African LRL pairs (Swahili, Amharic, Tigrigna, Oromo, Somali [SATOS]). We collected the available resources on the SATOS languages to evaluate the current state of NMT for LRLs. Our evaluation, comparing a baseline single language pair NMT model against semi-supervised learning, transfer learning, and multilingual modeling, shows significant performance improvements both in the En-LRL and LRL-En directions. In terms…
Language is an essential factor of emancipation. Unfortunately, most of the more than 2,000 African languages are low-resourced. The community has recently used machine translation to revive and strengthen several African languages. However, the trained models are often bilingual, resulting in a potentially exponential number of models to train and maintain to cover all possible translation directions. Additionally, bilingual models do not leverage the similarity between some of the languages. Consequently, multilingual neural machine translation (NMT) is gaining considerable interest, especia…
Cross-lingual transfer of multilingual models on low resource African Languages
School of Computer Science and Engineering, Vellore Institute of Technology（韦洛尔理工学院计算机科学与工程学院）；Department of Computer Science, University of Pretoria（比勒陀利亚大学计算机科学系）
African Institute for Mathematical Sciences（非洲数学科学研究所）；University of Cape Town（开普敦大学）；South African Astronomical Observatory（南非天文台）
Low-resource African languages have not fully benefited from the progress in neural machine translation because of a lack of data. Motivated by this challenge we compare zero-shot learning, transfer learning and multilingual learning on three Bantu languages (Shona, isiXhosa and isiZulu) and English. Our main target is English-to-isiZulu translation for which we have just 30,000 sentence pairs, 28% of the average size of our other corpora. We show the importance of language similarity on the performance of English-to-isiZulu transfer learning based on English-to-isiXhosa and English-to-Shona p…
The University of Tokyo（东京大学）；Carnegie Mellon University（卡内基梅隆大学）
Reproducible benchmarks are crucial in driving progress of machine translation research. However, existing machine translation benchmarks have been mostly limited to high-resource or well-represented languages. Despite an increasing interest in low-resource machine translation, there are no standardized reproducible benchmarks for many African languages, many of which are used by millions of speakers but have less digitized textual data. To tackle these challenges, we propose AfroMT, a standardized, clean, and reproducible machine translation benchmark for eight widely spoken African languages…
Multilingual pre-trained language models (PLMs) have demonstrated impressive performance on several downstream tasks for both high-resourced and low-resourced languages. However, there is still a large performance drop for languages unseen during pre-training, especially African languages. One of the most effective approaches to adapt to a new language is \textit{language adaptive fine-tuning} (LAFT) -- fine-tuning a multilingual PLM on monolingual texts of a language using the pre-training objective. However, adapting to a target language individually takes a large disk space and limits the c…
Improving Multilingual Math Reasoning for African Languages
The African Research Collective（非洲研究集体）；Masakhane NLP；University of Waterloo（滑铁卢大学）；Mila, McGill University（Mila，麦吉尔大学）；Canada CIFAR AI Chair（加拿大CIFAR人工智能 chair）
GradSim: Gradient-Based Language Grouping for Effective Multilingual Training
Bosch Center for Artificial Intelligence（博世人工智能中心）；LMU Munich（慕尼黑大学）；Hochschule der Medien（斯图加特传媒学院）；Karlsruhe University of Applied Sciences（卡尔斯鲁厄应用技术大学）
Searching for an available, reliable, official, and understandable information is not a trivial task due to scattered information across the internet, and the availability lack of governmental communication channels communicating with African dialects and languages. In this paper, we introduce an Artificial Intelligence Powered chatbot for crisis communication that would be omnichannel, multilingual and multi dialectal. We present our work on modified StarSpace embedding tailored for African dialects for the question-answering task along with the architecture of the proposed chatbot system and…
Existing data-to-text generation datasets are mostly limited to English. To address this lack of data, we create Table-to-Text in African languages (TaTa), the first large multilingual table-to-text dataset with a focus on African languages. We created TaTa by transcribing figures and accompanying text in bilingual reports by the Demographic and Health Surveys Program, followed by professional translation to make the dataset fully parallel. TaTa includes 8,700 examples in nine languages including four African languages (Hausa, Igbo, Swahili, and Yorùbá) and a zero-shot test language (Russian).…
Language models are the foundation of current neural network-based models for natural language understanding and generation. However, research on the intrinsic performance of language models on African languages has been extremely limited, which is made more challenging by the lack of large or standardised training and evaluation sets that exist for English and other high-resource languages. In this paper, we evaluate the performance of open-vocabulary language models on low-resource South African languages, using byte-pair encoding to handle the rich morphology of these languages. We evaluate…
TUM（慕尼黑工业大学）；Mila - Quebec AI Institute（米拉-魁北克人工智能研究所）；University of Cape Town（开普敦大学）；African Institute for Mathematical Sciences（非洲数学科学研究所）；Luleå University of Technology（吕勒奥理工大学）；LIAAD-INESC TEC（LIAAD-INESC科技与工程研究所）；Uppsala University（乌普萨拉大学）；Ford Motor Company（福特汽车公司）；University of Chinese Academy of Sciences（中国科学院大学）；Ahmadu Bello University（艾哈迈德·贝罗大学）；University of the Witwatersrand（威特沃特斯兰德大学）；Saarland University（萨尔大学）
We participated in the WMT 2022 Large-Scale Machine Translation Evaluation for the African Languages Shared Task. This work describes our approach, which is based on filtering the given noisy data using a sentence-pair classifier that was built by fine-tuning a pre-trained language model. To train the classifier, we obtain positive samples (i.e. high-quality parallel sentences) from a gold-standard curated dataset and extract negative samples (i.e. low-quality parallel sentences) from automatically aligned parallel data by choosing sentences with low alignment scores. Our final machine transla…
Mafoko: Structuring and Building Open Multilingual Terminologies for South African NLP
Data Science for Social Impact, Dept. of Computer Science, University of Pretoria（南非普里尼亚大学计算机科学系数据科学与社会影响研究中心）；AfriDSAI, University of Pretoria（南非普里尼亚大学非洲数据科学与人工智能研究所）；Lelapa AI（莱拉帕人工智能）；Economics and Management Sciences, University of the Free State（南非自由州大学经济与管理科学系）；Interdisciplinary Centre for Digital Futures, University of the Free State（南非自由州大学跨学科数字未来研究中心）
Multilingual transformer models like mBERT and XLM-RoBERTa have obtained great improvements for many NLP tasks on a variety of languages. However, recent works also showed that results from high-resource languages could not be easily transferred to realistic, low-resource scenarios. In this work, we study trends in performance for different amounts of available resources for the three African languages Hausa, isiXhosa and Yorùbá on both NER and topic classification. We show that in combination with transfer learning or distant supervision, these models can achieve with as little as 10 or 100 l…
We present our first efforts towards building a single multilingual automatic speech recognition (ASR) system that can process code-switching (CS) speech in five languages spoken within the same population. This contrasts with related prior work which focuses on the recognition of CS speech in bilingual scenarios. Recently, we have compiled a small five-language corpus of South African soap opera speech which contains examples of CS between 5 languages occurring in various contexts such as using English as the matrix language and switching to other indigenous languages. The ASR system presente…
NLNDE at SemEval-2023 Task 12: Adaptive Pretraining and Source Language Selection for Low-Resource Multilingual Sentiment Analysis
Bosch Center for Artificial Intelligence（博世人工智能中心）；Center for Information and Language Processing (CIS), LMU Munich（慕尼黑大学语言信息处理中心）；Karlsruhe University of Applied Sciences（卡尔斯鲁厄应用科学大学）
AfriMTE and AfriCOMET: Enhancing COMET to Embrace Under-resourced African Languages
University College London（伦敦大学学院）；Masakhane NLP（Masakhane自然语言处理组织）；University of Maryland（马里兰大学）；University of Oxford（牛津大学）；Unbabel（Unbabel公司）；Instituto Superior Técnico（高等技术学院）；INESC-ID（INESC-ID研究所）；ENSIAS（国家高等计算机与系统分析学院）；SADiLaR（南非洲数字语言资源中心）；Aston University（阿斯顿大学）；University of Eastern Finland（东芬兰大学）；Luleå University of Technology（吕勒奥理工大学）；Fudan University（复旦大学）；Conservatoire National des Arts et Métiers（法国国立工艺学院）；Lelapa AI（Lelapa人工智能公司）；Imperial College London（帝国理工学院）；University of Deusto（德乌斯托大学）
AfroLM: A Self-Active Learning-based Multilingual Pretrained Language Model for 23 African Languages
Mila Quebec AI Institute（米拉魁北克人工智能研究所）；McGill University（麦吉尔大学）；Instituto Politécnico Nacional（国家理工学院）；Uppsala University（乌普萨拉大学）；Universidad de Deusto（德乌斯托大学）；Ashesi University（阿希西大学）；Montclair State University（蒙特克莱尔州立大学）；The College of Saint Rose（圣罗斯学院）；Technical University of Munich（慕尼黑工业大学）
AfriqueLLM: How Data Mixing and Model Architecture Impact Continued Pre-training for African Languages
McGill University（麦吉尔大学）；Mila-Quebec AI Institute（魁北克AI研究所）；LMU Munich & Munich Center for Machine Learning（慕尼黑大学及慕尼黑机器学习中心）；Microsoft AI for Good Research Lab（微软AI for Good研究实验室）
Almost none of the 2,000+ languages spoken in Africa have widely available automatic speech recognition systems, and the required data is also only available for a few languages. We have experimented with two techniques which may provide pathways to large vocabulary speech recognition for African languages: multilingual modeling and self-supervised learning. We gathered available open source data and collected data for 15 languages, and trained experimental models using these techniques. Our results show that pooling the small amounts of data available in multilingual end-to-end models, and pr…
Virtual assistants and text chatbots have recently been gaining popularity. Given the short message nature of text-based chat interactions, the language identification systems of these bots might only have 15 or 20 characters to make a prediction. However, accurate text language identification is important, especially in the early stages of many multilingual natural language processing pipelines. This paper investigates the use of a naive Bayes classifier, to accurately predict the language family that a piece of text belongs to, combined with a lexicon based classifier to distinguish the spec…
Masakhane NLP（Masakhane自然语言处理社区）；Coqui（Coqui公司）；Saarland University（萨尔大学）；CLEAR Global（全球清晰语言组织）；Col·lectivaT（Col·lectivaT机构）；SIL International（国际暑期语言学院）；Leibniz Universität Hannover（汉诺威莱布尼茨大学）；Johns Hopkins University（约翰斯·霍普金斯大学）；Niger-Volta LTI（尼日尔-沃尔特语言技术倡议）；Carnegie Mellon University（卡内基梅隆大学）；Technical University of Munich（慕尼黑工业大学）；Makerere University（马凯雷雷大学）；Ewegbe Akademi（埃韦格贝学院）；Kwame Nkrumah University of Science and Technology（夸梅·恩克鲁玛科技大学）
BibleTTS is a large, high-quality, open speech dataset for ten languages spoken in Sub-Saharan Africa. The corpus contains up to 86 hours of aligned, studio quality 48kHz single speaker recordings per language, enabling the development of high-quality text-to-speech models. The ten languages represented are: Akuapem Twi, Asante Twi, Chichewa, Ewe, Hausa, Kikuyu, Lingala, Luganda, Luo, and Yoruba. This corpus is a derivative work of Bible recordings made and released by the Open.Bible project from Biblica. We have aligned, cleaned, and filtered the original recordings, and additionally hand-che…
AfriNames: Most ASR models "butcher" African Names
Intron Health Inc（Intron健康公司）；Georgia Institute of Technology（佐治亚理工学院）；AI Saturdays Lagos（拉各斯AI星期六组织）；CISPA Helmholtz Center for Information Security（亥姆霍兹信息安全中心（CISPA））；McGill University（麦吉尔大学）；Mila Quebec AI Institute（米拉魁北克人工智能研究所）；Lelapa AI（莱拉帕人工智能公司）；Lanfrica（Lanfrica公司）；Instituto Politécnico Nacional（国立理工学院）；Technical University of Munich（慕尼黑工业大学）；Idiap Research Institute（Idiap研究所）；Ford Motor Company（福特汽车公司）；Masakhane NLP（Masakhane自然语言处理组织）
该研究将 ASR 对非洲姓名的识别失败建模为分布偏移，并通过多语言预训练、数据增强和非洲口音微调，使相对 WER 改善 81.5%。
Charting the Landscape of African NLP: Mapping Progress and Shaping the Road Ahead
Saarland University, Saarland Informatics Campus（萨尔兰大学，萨尔兰信息学校区）；LMU Munich and Munich Center for Machine Learning（慕尼黑大学及慕尼黑机器学习中心）；Mila - Quebec AI Institute, McGill University & Canada CIFAR AI Chair（魁北克人工智能研究所，麦吉尔大学及加拿大 CIFAR 人工智能 chair）
HausaNLP at SemEval-2023 Task 12: Leveraging African Low Resource TweetData for Sentiment Analysis
Kaduna State University（卡杜纳州立大学）；University of Bucharest（布加勒斯特大学）；University of Abuja（阿布贾大学）；Nile University（尼罗河大学）；Universiti Teknologi PETRONAS（马来西亚石油科技大学）；Bayero University Kano（卡诺贝罗大学）；Shehu Shagari College of Education（谢胡·沙加里教育学院）；Ahmadu Bello University, Zaria（扎里亚艾哈迈德·贝罗大学）；HausaNLP（豪萨语自然语言处理研究组）
AfriMTEB and AfriE5: Benchmarking and Adapting Text Embedding Models for African Languages
University of Toronto（多伦多大学）；Mila - Quebec AI Institute, McGill University（魁北克AI研究院，麦吉尔大学）；Saarland University, Saarland Informatic Campus（萨尔兰大学，萨尔兰信息学院）；Canada CIFAR AI Chair（加拿大CIFAR人工智能主席）
