You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
abstract = "We present the process of building linguistic corpora of the Portuguese-related Gulf of Guinea creoles, a cluster of four historically related languages: Santome, Angolar, Principense and Fa dAmb{\^o}. We faced the typical difficulties of languages lacking an official status, such as lack of standard spelling, language variation, lack of basic language instruments, and small data sets, which comprise data from the late 19th century to the present. In order to tackle these problems, the compiled written and transcribed spoken data collected during field work trips were adapted to a normalized spelling that was applied to the four languages. For the corpus compilation we followed corpus linguistics standards. We recorded meta data for each file and added morphosyntactic information based on a part-of-speech tag set that was designed to deal with the specificities of these languages. The corpora of three of the four creoles are already available and searchable via an online web interface.",
339
339
language = "Guinea Creole",
340
340
}
341
+
342
+
@inproceedings{armstrong-etal-2022-jampatoisnli,
343
+
title = "{J}am{P}atois{NLI}: A {J}amaican {P}atois Natural Language Inference Dataset",
344
+
author = "Armstrong, Ruth-Ann and
345
+
Hewitt, John and
346
+
Manning, Christopher",
347
+
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2022",
348
+
month = dec,
349
+
year = "2022",
350
+
address = "Abu Dhabi, United Arab Emirates",
351
+
publisher = "Association for Computational Linguistics",
Haitian Kreyol,CMU Haitian Corpus,Speech and Text Corpora,Verified,,,http://www.speech.cs.cmu.edu/haitian/,
7
7
Haitian Kreyol,Corpus of Northern Haitian Creole,Audio and Transcription,Not open source,,,https://www.indiana.edu/~creole/,
8
8
Hawaiian Pidgin,Multilingual Hawai'i Linguistic Landscape Corpus ,Image Repository with Annotations,"Verified but currently unavailable, check back later","(Purschke, 2021)",https://www.degruyter.com/document/doi/10.1515/lingvan-2019-0032/html,,
9
+
Jamaican Creole English,JamPatoisNLI,NLI,Verified,"(Armstrong et al., 2022)",https://aclanthology.org/2022.findings-emnlp.389/,https://github.com/ruth-ann/jampatoisnli,
9
10
Malaccan Portuguese Creole,Endangered Language Archive,"Audio, Video, Transcriptions, Translations",Not open source; Membership required,,,http://elar.soas.ac.uk/deposit/0123,
10
11
Maurtian Creole,ALLEX Project,Concordance of 200k Words,Not open source,,,http://www.edd.uio.no/allex/corpus/africanlang.html,
11
12
Nigerian Pidgin,NaijaSynCor ,Speech Recognition,Verified,"(Bigi et al., 2017)",https://hal.archives-ouvertes.fr/hal-01705707/document,,
0 commit comments