Second AmericasNLP Competition: Speech-to-Text Translation for Indigenous Languages of the Americas
What?The Second AmericasNLP Competition on Speech-to-Text Translation for Indigenous Languages of the Americas is an official NeurIPS 2022 competition aimed at encouraging the development of machine translation (MT) systems for indigenous languages of the Americas. The overall goal is to develop new speech-to-text translation technology for Indigenous languages, and participants will build systems for 3 tasks: (1) automatic speech recognition (ASR) for an Indigenous language (Task 1), (2) text-to-text translation between an Indigenous language and a high-resource language (Task 2), and (3) speech-to-text translation between an Indigenous language and a high-resource language (Task 3, our main task).
Why?Many Indigenous languages of the Americas are so-called low-resource languages: parallel data with other languages as needed to train speech-to-text MT systems is limited. This means that many approaches designed for translating between high-resource languages – such as English, Spanish, or Portuguese – are not directly applicable or perform poorly. Additionally, many Indigenous languages exhibit linguistic properties uncommon among languages frequently studied in natural language processing (NLP), e.g., many are polysynthetic or tonal. This constitutes an additional difficulty. We want to motivate researchers to take on the challenge of developing speech-to-text MT systems for Indigenous languages.
How?We invite submissions of speech-to-text MT results (as well as of results for the subtasks of ASR and text-to-text translation) obtained by systems built for Indigenous languages. We will provide training and evaluation data to the participants, but there are no limits on what outside resources – such as additional data or pretrained systems – participants can use, with the exception of the datasets listed here. This should go without saying, but we ask that participants don't translate (or transcribe, in the case of ASR) the test input by hand. The main metrics of this competition are ChrF (Popović, 2015) for Tasks 2 and 3 and character error rate for Task 1. Participants can submit results for as many language pairs as they like, but only teams that participate for all language pairs for a task are entering the official ranking. We provide an evaluation script and a baseline MT system to help participants getting started quickly. If you are interested in this competition, please register here.
System SubmissionPlease send your system outputs to abteen[dot]ebrahimi[at]colorado[dot]edu and katharina[dot]kann[at]colorado[dot]edu. The subject of your email should be "NeurIPS–AmericasNLP 2022; Competition Submission; Task(s) ‹TASK NUMBER(S)›; ‹TEAM NAME›". The content of your submission email should be as follows:
- Line 1: Team name.
- Line 2: Names of all team members.
- Line 3: A link to a GitHub repository with code that can be used to reproduce your results. Submissions without this line will be mentioned in the overview paper but will not be competing for prizes.
- Next: Names of all language pairs you are sending submissions for, one per line, in an order of your choice (we will use this to double-check that we got all files you intended to send), followed by a semicolon and the task(s) for which you are sending outputs for that pair, another semicolon, and the number of different versions you are submitting.
- Next: The official names or links to all datasets besides the official training and validation data you have used, one per line. Do not include pretrained models here.
LanguagesThe following language pairs are featured in the NeurIPS–AmericasNLP 2022 competition:
Data and Baseline SystemA script to download the datasets for the competition, an evalution script, and the official baselines can be found in our GitHub.
PrizesAs long as the best performing systems beat our baselines, the corresponding teams will be awarded the following prizes:
- Task 1: $500 for the best team
- Task 2: $500 for the best team
- Task 3 (main task): $1000 for the best team, $500 for the second best team, $300 for the third best team
Release of pilot data and evaluation script: May 23, 2022 Release of training and development data and baseline systems: June 6, 2022
- Release of test input/start of evaluation phase: September 16, 2022
- Submission of translations by participants/end of competition: September 30, 2022
- Announcements of results: October 4, 2022
- Submission of system description papers by the participants: October 14, 2022
- Notification of acceptance: October 21, 2022
- Camera-ready papers and deadline for competition overview paper: October 31, 2022
- Competition track meeting at NeurIPS (virtual event): December 2022
OrganizersManuel Mager, Katharina Kann, Abteen Ebrahimi, Arturo Oncevay, Rodolfo Zevallos, Adam Wiemerslage, Pavel Denisov, John E. Ortega, Kristine Stenzel, Aldo Alvarez, Luis Chiruzzo, Rolando Coto-Solano, Hilaria Cruz, Sofía Flores-Solórzano, Ivan Vladimir Meza Ruiz, Alexis Palmer, Ngoc Thang Vu