1. |
- Adelani, David, et al.
(author)
-
A Few Thousand Translations Go A Long Way! Leveraging Pre-trained Models for African News Translation
- 2022
-
In: NAACL 2022. - Stroudsburg : Association for Computational Linguistics. - 9781955917711 ; , s. 3053-3070
-
Conference paper (peer-reviewed)abstract
- Recent advances in the pre-training of language models leverage large-scale datasets to create multilingual models. However, low-resource languages are mostly left out in these datasets. This is primarily because many widely spoken languages are not well represented on the web and therefore excluded from the large-scale crawls used to create datasets. Furthermore, downstream users of these models are restricted to the selection of languages originally chosen for pre-training. This work investigates how to optimally leverage existing pre-trained models to create low-resource translation systems for 16 African languages. We focus on two questions: 1) How can pre-trained models be used for languages not included in the initial pre-training? and 2) How can the resulting translation models effectively transfer to new domains? To answer these questions, we create a new African news corpus covering 16 languages, of which eight languages are not part of any existing evaluation dataset. We demonstrate that the most effective strategy for transferring both to additional languages and to additional domains is to fine-tune large pre-trained models on small quantities of high-quality translation data.
|
|
2. |
- Adelani, David Ifeoluwa, et al.
(author)
-
MasakhaNER 2.0: Africa-centric Transfer Learning for Named Entity Recognition
- 2022
-
In: Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing. - : Association for Computational Linguistics (ACL). ; , s. 4488-4508
-
Conference paper (peer-reviewed)abstract
- 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.
|
|
3. |
- Bamutura, David, 1984, et al.
(author)
-
Towards computational resource grammars for runyankore and rukiga
- 2020
-
In: LREC 2020 - 12th International Conference on Language Resources and Evaluation, Conference Proceedings. - : European Language Resources Association. ; , s. 2846-2854
-
Conference paper (peer-reviewed)abstract
- In this paper, we present computational resource grammars of Runyankore and Rukiga (R&R) languages. Runyankore and Rukiga are two under-resourced Bantu Languages spoken by about 6 million people indigenous to South Western Uganda, East Africa. We used Grammatical Framework (GF), a multilingual grammar formalism and a special-purpose functional programming language to formalise the descriptive grammar of these languages. To the best of our knowledge, these computational resource grammars are the first attempt to the creation of language resources for R&R. In Future Work, we plan to use these grammars to bootstrap the generation of other linguistic resources such as multilingual corpora that make use of data-driven approaches to natural language processing feasible. In the meantime, they can be used to build Computer-Assisted Language Learning (CALL) applications for these languages among others.
|
|
4. |
- Adelani, David Ifeoluwa, et al.
(author)
-
MasakhaNER: Named Entity Recognition for African Languages
- 2021
-
In: Transactions of the Association for Computational Linguistics. - : MIT Press. - 2307-387X. ; 9, s. 1116-1131
-
Journal article (peer-reviewed)abstract
- We take a step towards addressing the under-representation of the African continent in NLP research by bringing together different stakeholders to create the first large, publicly available, high-quality dataset for named entity recognition (NER) in ten African languages. We detail the characteristics of these languages to help researchers and practitioners better understand the challenges they pose for NER tasks. We analyze our datasets and conduct an extensive empirical evaluation of state-of-the-art methods across both supervised and transfer learning settings. Finally, we release the data, code, and models to inspire future research on African NLP.
|
|
5. |
- Ismail, Kamukama, et al.
(author)
-
Spatio-temporal trends and distribution patterns of typhoid disease in Uganda from 2012 to 2017
- 2021
-
In: Geospatial health. - : PAGEPress Publications. - 1970-7096 .- 1827-1987. ; 15:2
-
Journal article (peer-reviewed)abstract
- Typhoid disease continues to be a global public health burden. Uganda is one of the African countries characterized by high incidences of typhoid disease. Over 80% of the Ugandan districts are endemic for typhoid, largely attributable to lack of reliable knowledge to support disease surveillance. Spatial-temporal studies exploring major characteristics of the disease within the local population have remained limited in Uganda. The main goal of the study was to reveal spatial-temporal trends and distribution patterns of typhoid disease in Uganda for the period 2012 to 2017. Spatial-temporal statistics revealed monthly and annual trends of the disease at both regional and national levels. Results show that outbreaks occurred during 2015 and 2017 in central and eastern regions, respectively. Spatial scan statistic using the discrete Poisson model revealed spatial clusters of the disease for each of the years from 2012 to 2017, together with populations at risk. Most of the disease clustering was in the central region, followed by western and eastern regions (P <0.01). The northern region was the safest throughout the study period. This knowledge helps surveillance teams to i) plan and enforce preventive measures; ii) effectively prepare for outbreaks; iii) make targeted interventions for resource optimization; and iv) evaluate effectiveness of the intervention methods in the study period. This exploratory research forms a foundation of using Geographical Information Systems (GIS) in other related subsequent research studies to discover hidden spatial patterns that are difficult to discover with conventional methods.
|
|
6. |
|
|
7. |
- Tiedemann, Jörg, et al.
(author)
-
Translating Transliterations
- 2009
-
In: International Journal of Computing and ICT Research. - 1818-1139. ; 3:1, s. 33-41
-
Journal article (peer-reviewed)
|
|