Search
Now showing items 51-60 of 88
NCHLT Xitsonga RoBERTa language model
(North-West University; Centre for Text Technology (CTexT), 2023-05-01)
Contextual masked language model based on the RoBERTa architecture (Liu et al., 2019). The model is trained as a masked language model and not fine-tuned ...
Autshumato Monolingual Xitsonga Corpus
(CTexT® (Centre for Text Technology, North-West University), 2022-09-30)
Monolingual corpus for Xitsonga. The data is given as a single UTF-8 text file, with each segment on a newline. The data was specifically selected and ...
Autshumato Machine Translation Web Service (MTWS)
(Centre for Text Technology; North-West University, 2018-03-01) ~ - Resource Index
The MTWS is a unified interface through which anyone can gain access to the MT systems developed in the Autshumato project. It can provide sentence, ...
Speect
(Meraka Institute, CSIR, 2013-07-15) ~ - Resource Catalogue
Speect is a multilingual text-to-speech (TTS) system. It offers a full TTS system (text analysis which decodes the text, and speech synthesis, which ...
Multilingual Life Orientation Intermediate Phase Terminology List
(Terminology Coordination Section of the National Language Service, Department of Arts and Culture, 2017-03-03) ~ - Resource Index
1628 English source terms with their equivalents in the ten other official South African languages. The terms were excerpted from life orientation ...
Multilingual Parliamentary / Political Terminology List
(Terminology Coordination Section of the National Language Service, Department of Arts and Culture, 2017-03-03) ~ - Resource Index
502 English source terms with their equivalents in the ten other official South African languages. The project built on a 2003 initiative of the national ...
AStudio
(North-West University; Stellenbosch University; University of Transkei; University of Free State (Qwa-Qwa campus); Rhodes University; University of KwaZulu-Natal; University of Western Cape, 2015-01-07) ~ - Resource Index
This software incorporates a graphic interface that allows for the development of a flowchart representation of the state machine that will form the ...
NCHLT Xitsonga word2vec-Skipgram embeddings
(North-West University; Centre for Text Technology (CTexT), 2023-05-01)
Static word embeddings for the Skipgram flavour of the word2vec (w2v) architecture (Mikolov et al., 2013). The embedding provides real-valued vector ...
NCHLT Text Web Services
(SADiLaR; North-West University, 2018-03-01) ~ - Resource Index
A web service that provides access to seven core technologies in ten South African languages, including:
* Tokenisers
* Sentence separators
* ...
Open Spell (v1.0)
(Meraka Institute, CSIR; TEIR; ICSI at University of California (Berkeley), 2013-07-01) ~ - Resource Index
Open Spell is spelling game that provides spelling exercises (in the language education domain) to teach spelling skills to schoolchildren between the ...