Skip to content

Commit fc2019d

Browse files
mdelhoneuxmdelhoneux
committed
modified language taxonomy to match the table
2 parents c729bd9 + 4679425 commit fc2019d

File tree

3 files changed

+33
-33
lines changed

3 files changed

+33
-33
lines changed

‎_bibliography/papers.bib‎

Lines changed: 16 additions & 16 deletions
Original file line numberDiff line numberDiff line change
@@ -18,7 +18,7 @@ @article{DBLP:journals/corr/BajpaiPHC17
1818
}
1919

2020
@inproceedings{dabre-etal-2014-anou,
21-
title = "Anou Tradir: Experiences In Building Statistical Machine Translation Systems For Mauritian Languages {--} Creole, {E}nglish, {F}rench",
21+
title = "Anou Tradir: Experiences In Building Statistical Machine Translation Systems For Mauritian Creole Languages {--} Creole, {E}nglish, {F}rench",
2222
author = "Dabre, Raj and
2323
Sukhoo, Aneerav and
2424
Bhattacharyya, Pushpak",
@@ -29,7 +29,7 @@ @inproceedings{dabre-etal-2014-anou
2929
publisher = "NLP Association of India",
3030
url = "https://aclanthology.org/W14-5113",
3131
pages = "82--88",
32-
language = {Mauritian}
32+
language = {Mauritian Creole}
3333
}
3434

3535

@@ -123,22 +123,22 @@ @article{sebba1998phonology
123123

124124

125125
@book{baker2007making,
126-
title={The making of Mauritian Creole. Analyses diachroniques {\`a} partir des textes anciens},
126+
title={The making of Mauritian Creole Creole. Analyses diachroniques {\`a} partir des textes anciens},
127127
author={Baker, Philip and Sing, Guillaume Fon},
128128
number={9},
129129
year={2007},
130130
publisher={Battlebridge},
131-
language={Mauritian}
131+
language={Mauritian Creole}
132132
}
133133

134134

135-
@article{Oyewusi2021NaijaNERC,
136-
title={NaijaNER : Comprehensive Named Entity Recognition for 5 Nigerian Languages},
135+
@article{Oyewusi2021Nigerian PidginNERC,
136+
title={Nigerian PidginNER : Comprehensive Named Entity Recognition for 5 Nigerian Languages},
137137
author={Wuraola Fisayo Oyewusi and Olubayo Adekanmbi and Ife Okoh and Vitus Onuigwe and Mary Idera Salami and Opeyemi Osakuade and Sharon Ibejih and Usman Abdullahi Musa},
138138
journal={ArXiv},
139139
year={2021},
140140
volume={abs/2105.00810},
141-
language={Naija}
141+
language={Nigerian Pidgin}
142142
}
143143

144144
@article{adelani-etal-2021-masakhaner,
@@ -221,7 +221,7 @@ @article{Ajisafe2020TowardsET
221221
journal={ArXiv},
222222
year={2020},
223223
volume={abs/2010.11123},
224-
language={Naija}
224+
language={Nigerian Pidgin}
225225
}
226226

227227
@article{Oyewusi2020SemanticEO,
@@ -230,7 +230,7 @@ @article{Oyewusi2020SemanticEO
230230
journal={ArXiv},
231231
year={2020},
232232
volume={abs/2003.12450},
233-
language={Naija}
233+
language={Nigerian Pidgin}
234234
}
235235

236236

@@ -239,14 +239,14 @@ @inproceedings{Munro10crowdsourcedtranslation
239239
title = {Crowdsourced translation for emergency response in haiti: the global collaboration of local knowledge},
240240
booktitle = {In Relief 2.0 in Haiti},
241241
year = {2010},
242-
language={Haitian}
242+
language={Haitian Kreyol}
243243
}
244244

245245
@inproceedings{Bigi2017DevelopingRF,
246-
title={Developing Resources for Automated Speech Processing of the African Language Naija (Nigerian Pidgin)},
246+
title={Developing Resources for Automated Speech Processing of the African Language Nigerian Pidgin (Nigerian Pidgin)},
247247
author={B. Bigi and B. Caron and Oyelere S. Abiola},
248248
year={2017},
249-
language={Naija}
249+
language={Nigerian Pidgin}
250250
}
251251

252252
@article{Ogueji2019PidginUNMTUN,
@@ -264,7 +264,7 @@ @article{Ahia2020TowardsSA
264264
journal={ArXiv},
265265
year={2020},
266266
volume={abs/2003.12660},
267-
language={Naija}
267+
language={Nigerian Pidgin}
268268
}
269269

270270
@inproceedings{obighosh2019naija,
@@ -290,7 +290,7 @@ @inproceedings{caron-etal-2019-surface
290290
url = "https://www.aclweb.org/anthology/W19-7803",
291291
doi = "10.18653/v1/W19-7803",
292292
pages = "13--24",
293-
language={Naija}
293+
language={Nigerian Pidgin}
294294
}
295295

296296
@article{Oyewusi2020SemanticEO,
@@ -299,7 +299,7 @@ @article{Oyewusi2020SemanticEO
299299
journal={ArXiv},
300300
year={2020},
301301
volume={abs/2003.12450},
302-
language={Naija}
302+
language={Nigerian Pidgin}
303303
}
304304

305305
@inproceedings{hu-etal-2011-value,
@@ -317,7 +317,7 @@ @inproceedings{hu-etal-2011-value
317317
publisher = "Association for Computational Linguistics",
318318
url = "https://aclanthology.org/W11-2148",
319319
pages = "399--404",
320-
language= "Haitian",
320+
language= "Haitian Kreyol",
321321
}
322322

323323
@inproceedings{hagemeijer-etal-2014-gulf,

‎_pages/home.md‎

Lines changed: 16 additions & 16 deletions
Original file line numberDiff line numberDiff line change
@@ -16,13 +16,20 @@ social: false # includes social icons at the bottom of the page
1616

1717
This page aims to centralize NLP resources for Creoles. This is an open community effort and we welcome updates via [pull requests](https://docs.github.com/es/pull-requests/collaborating-with-pull-requests/proposing-changes-to-your-work-with-pull-requests/about-pull-requests) on this website's [github repository](https://github.com/creole-nlp/creole-nlp.github.io).
1818

19-
Below is a table summarizing resources and their availability. Papers on Creoles are collected [here](/papers).
19+
Below is a table summarizing resources and their availability. The resource column links to the official url, where applicable. The status column includes links that have been verified, where applicable.
20+
Papers on Creoles are collected [here](/papers).
2021

2122
| Language | Resource | Description | Status |
2223
|----------------------------------------|-------------------------------------------------------------------------------------|-----------------------------------------------------------|--------------------------------------|
23-
| Haitian Kreyol | Haitian Disaster Response Corpus ([Munro, 2010](https://aclanthology.org/2010.amta-workshop.1/); [Callison-Burch et al., 2011](https://aclanthology.org/volumes/W11-21/)) | SMS | Verified; E-mail authors for access. |
24-
|^^ | [CMU Haitian Corpus](http://www.speech.cs.cmu.edu/haitian/) | Speech and Text Corpora | Verified |
24+
| Antillean Creole | [CREOLORAL](http://ircom.corpus-ir.fr/site/description_projet.php?projet=CREOLORAL) | Audio, Transcriptions, and Translations | Not open source |
25+
| Bastimentos Creole English | [Endangered Language Archive](http://elar.soas.ac.uk/deposit/0171) | Audio, Video, Transcriptions, Translations | Not open source; Membership required |
26+
| Gulf of Guinea Creoles | The Gulf of Guinea Creole Corpora ([Hagemeijer et al., 2014](https://aclanthology.org/L14-1376/)) | Document Scans and Transcriptions | Limited Verifiability |
27+
| Haitian Kreyol | [Corpus of Northern Haitian Creole](https://www.indiana.edu/~creole/) | Audio and Transcription | Not open source |
28+
|^^ | Haitian Disaster Response Corpus ([Munro, 2010](https://aclanthology.org/2010.amta-workshop.1/); [Callison-Burch et al., 2011](https://aclanthology.org/volumes/W11-21/)) | SMS | Verified; E-mail authors for access. |
29+
|^^ | [CMU Haitian Corpus](http://www.speech.cs.cmu.edu/haitian/) | Speech and Text Corpora | [Verified](http://www.speech.cs.cmu.edu/haitian/) |
2530
| Hawaiian Pidgin | Multilingual Hawai'i Linguistic Landscape Corpus ([Purschke, 2021](https://www.degruyter.com/document/doi/10.1515/lingvan-2019-0032/html)) | Image Repository with Annotations | Verified |
31+
| Malaccan Portuguese Creole | [Endangered Language Archive](http://elar.soas.ac.uk/deposit/0123) | Audio, Video, Transcriptions, Translations | Not open source; Membership required |
32+
| Mauritian Creole | [ALLEX Project](http://www.edd.uio.no/allex/corpus/africanlang.html) | Concordance of 200k Words | Not open source |
2633
| Nigerian Pidgin | NaijaSynCor ([Bigi et al., 2017](https://hal.archives-ouvertes.fr/hal-01705707/document)) | Speech Recognition | Verified |
2734
|^^ | JW300 Corpus ([Agić and Vulić, 2019](https://aclanthology.org/P19-1310/)) | Parallel Texts for Machine Translation | Verified |
2835
|^^ | Pidgin UNMT ([Ogueji and Ahia, 2019](https://aclanthology.org/2021.mrl-1.11/)) | Monolingual Texts for Machine Translation | Verified |
@@ -31,22 +38,15 @@ Below is a table summarizing resources and their availability. Papers on Creoles
3138
|^^ | Speech-to-Text Nigerian Pidgin Dataset ([Ajisafe et al., 2020](https://arxiv.org/abs/2010.11123)) | Speech Recognition | Verified |
3239
|^^ | NaijaNER ([Oyewusi et al., 2021](https://arxiv.org/abs/2003.12450)) | Named Entity Recognition | Verified |
3340
|^^ | Masakhaner ([Adelani et al., 2021](https://aclanthology.org/2021.tacl-1.66/)) | Named Entity Recognition | Verified |
34-
| Reunionese Creole & Seychellois Creole | [Creolica](http://creolica.net/) | Text and Short Stories in HTML or PDFs | Verified |
41+
|^^ | Nigerian Pidgin Tweets ([Oyewusi et al., 2020](https://arxiv.org/abs/2003.12450)) | Sentiment Analysis | Not open source |
42+
| Portuguese Creole | CreolData ([Schang et al., 2005](https://www.cairn-int.info/article-E_RFLA_101_76--creoldata-a-lexical-database-on-creole.htm)) | Lexical Database | Not open source |
43+
| Reunionese Creole & Seychellois Creole | [Creolica](http://creolica.net/) | Text and Short Stories in HTML or PDFs | [Verified](http://creolica.net/) |
3544
| Singlish | National University of Singapore SMS Corpus ([Chen and Min-Yen, 2015](https://scholarbank.nus.edu.sg/handle/10635/137343)) | SMS | Verified |
3645
|^^ | Universal Dependencies for Colloquial Singaporean English ([Wang et al., 2017](https://aclanthology.org/P17-1159/)) | UD Treebank | Verified |
3746
|^^ | Webcrawler for Singaporean Hardware Forum ([Tan et al., 2020](https://aclanthology.org/2020.emnlp-main.455/)) | Webcrawler | Verified |
38-
| {Sri Lankan Malay} (Endangered) | The Language Archive ([Nordhoff, 2006](https://hdl.handle.net/1839/00-0000-0000-0007-F855-4)) | Audio and XML | Verified |
39-
| Antillean Creole | [CREOLORAL](http://ircom.corpus-ir.fr/site/description_projet.php?projet=CREOLORAL) | Audio, Transcriptions, and Translations | Not verifiable |
40-
| Bastimentos Creole English | [Endangered Language Archive](http://elar.soas.ac.uk/deposit/0171) | Audio, Video, Transcriptions, Translations | Not verifiable; |
41-
| Gulf of Guinea Creoles | The Gulf of Guinea Creole Corpora ([Hagemeijer et al., 2014](https://aclanthology.org/L14-1376/)) | Document Scans and Transcriptions | Limited Verifiability |
42-
| Haitian Kreyol | [Corpus of Northern Haitian Creole](https://www.indiana.edu/~creole/) | Audio and Transcription | Not verifiable |
43-
| Malaccan Portuguese Creole | [Endangered Language Archive](http://elar.soas.ac.uk/deposit/0123) | Audio, Video, Transcriptions, Translations | Not verifiable; Membership required |
44-
| Maurtian Creole | [ALLEX Project](http://www.edd.uio.no/allex/corpus/africanlang.html) | Concordance of 200k Words | Not verifiable |
45-
| Nigerian Pidgin | Nigerian Pidgin Tweets ([Oyewusi et al., 2020](https://arxiv.org/abs/2003.12450)) | Sentiment Analysis | Not Verifiable |
46-
| Portuguese Creole | CreolData ([Schang et al., 2005](https://www.cairn-int.info/article-E_RFLA_101_76--creoldata-a-lexical-database-on-creole.htm)) | Lexical Database | Not verifiable |
47-
| Singlish | Singlish Sentiment Lexicon ([Bajpai et al., 2017](https://arxiv.org/abs/1707.04408)) | Knowledge Base | Not Verifiable |
48-
|^^ | Singlish SenticNet ([Ho et al., 2018](https://ieeexplore.ieee.org/document/8628796)) | Sentiment Resource | Not Verifiable |
49-
47+
|^^ | Singlish Sentiment Lexicon ([Bajpai et al., 2017](https://arxiv.org/abs/1707.04408)) | Knowledge Base | Not open source |
48+
|^^ | Singlish SenticNet ([Ho et al., 2018](https://ieeexplore.ieee.org/document/8628796)) | Sentiment Resource | Not open source |
49+
| Sri Lankan Malay (Endangered) | The Language Archive ([Nordhoff, 2006](https://hdl.handle.net/1839/00-0000-0000-0007-F855-4)) | Audio and XML | Verified |
5050

5151

5252
<br>

‎_pages/publications.md‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -3,7 +3,7 @@ layout: page
33
permalink: /papers/
44
title: papers
55
description: papers by language
6-
languages: ['British Creole', 'Guinea Creole', 'Guyanese', 'Haitian', 'Mauritian', 'Naija', 'Singlish', 'West African Pidgin', ]
6+
languages: ['British Creole', 'Guinea Creole', 'Guyanese', 'Haitian Kreyol', 'Mauritian Creole', 'Nigerian Pidgin', 'Singlish', 'West African Pidgin', ]
77
nav: true
88
---
99
<div class="publications">

0 commit comments

Comments
 (0)