In this paper we describe the development of a text-to-speech system for Māori ‘Avaiki Nui (Cook Islands Māori). We provide details about the process of community-collaboration that was followed throughout the project, a continued engagement where we are trying to develop speech and language technology for the benefit of the community. During this process we gathered a group of recordings that we used to train a TTS system. When training we used two approaches, the HMM-system MaryTTS (Schröder et al., 2011) and the deep learning system FastSpeech2 (Ren et al., 2020). We performed two evaluation tasks on the models: First, we measured their quality by having the synthesized speech transcribed by ASR. The human produced ground truth had lower error rates (CER=4.3, WER=18), but the FastSpeech2 audio has lower error rates (CER=11.8 and WER=42.7) than the MaryTTS voice (CER=17.9 and WER=48.1). The second evaluation was a survey amongst speakers of the language so they could judge the voice’s quality. The ground truth was rated with the highest quality (MOS=4.6), but the FastSpeech2 voice had an overall quality of MOS=3.2, which was significantly higher than that of the MaryTTS synthesized recordings (MOS=2.0). We intend to use the FastSpeech2 model to create language learning tools for community members both on the Cook Islands and in the diaspora.

This paper presents a first attempt to apply Universal Dependencies (De Marneffe et al., 2021) to train a parser for Mauritian Creole (MC), a French-based Creole language spoken on the island of Mauritius. This paper demonstrates the construction of a 161-sentence (1007-token) treebank for MC and evaluates the performance of a part-of-speech tagger and Universal Dependencies parser trained on this data. The sentences were collected from publicly available grammar books (Syea, 2013) and online resources (Baker and Kriegel, 2013), as well as from government-produced school textbooks (Antonio-Françoise et al., 2021; Natchoo et al., 2017). The parser, trained with UDPipe 2 (Straka, 2018), reached F1 scores of UPOS=86.2, UAS=80.8 and LAS=69.8. This fares favorably when compared to models of similar size for other under-resourced Indigenous and Creole languages. We then address some of the challenges faced when applying UD to Creole languages in general and to Mauritian Creole in particular. The main challenge was the handling of spelling variation in the input. Other issues include the tagging of modal verbs, middle voice sentences, and parts of the tense-aspect-mood system (such as the particle fek).

We present experiments on Automatic Speech Recognition (ASR) for Bribri and Cabécar, two languages from the Chibchan family. We fine-tune four ASR algorithms (Wav2Vec2, Whisper, MMS & WavLM) to create monolingual models, with the Wav2Vec2 model demonstrating the best performance. We then proceed to use Wav2Vec2 for (1) experiments on training joint and transfer learning models for both languages, and (2) an analysis of the errors, with a focus on the transcription of tone. Results show effective transfer learning for both Bribri and Cabécar, but especially for Bribri. A post-processing spell checking step further reduced character and word error rates. As for the errors, tone is where the Bribri models make the most errors, whereas the simpler tonal system of Cabécar is better transcribed by the model. Our work contributes to developing better ASR technology, an important tool that could facilitate transcription, one of the major bottlenecks in language documentation efforts. Our work also assesses how existing pre-trained models and algorithms perform for genuine extremely low resource-languages.

This paper presents three experiments to test the most effective and efficient ASR pipeline to facilitate the documentation and preservation of endangered languages, which are often extremely low-resourced. With data from two languages in Nepal —Dzardzongke and Newar— we show that model improvements are different for different masses of data, and that transfer learning as well as a range of modifications (e.g. normalising amplitude and pitch) can be effective, but that a consistently-standardised orthography as NLP input and post-training dictionary corrections improve results even more.

This paper outlines the Universal Features tagging of a dependency treebank for Bribri, an Indigenous language of Costa Rica. Universal Features are a morphosyntactic tagging component of Universal Dependencies, which is a framework that aims to provide an annotation system inclusive of all languages and their diverse structures (Nivre et al., 2016; de Marneffe et al., 2021). We used a rule-based system to do a first-pass tagging of a treebank of 1572 words. After manual corrections, the treebank contained 3051 morphological features. We then used this morphologically-tagged treebank to train a UDPipe 2 parsing and tagging model. This model has a UFEATS precision of 80.5 ± 3.6, which is a statistically significant improvement upon the previously available FOMA-based morphological tagger for Bribri. An error analysis suggests that missing TAM and case markers are the most common problem for the model. We hope to use this model to expand upon existing treebanks and facilitate the construction of linguistically-annotated corpora for the language.

This paper presents the results of the first shared task about the creation of educational materials for three indigenous languages of the Americas.The task proposes to automatically generate variations of sentences according to linguistic features that could be used for grammar exercises.The languages involved in this task are Bribri, Maya, and Guarani.Seven teams took part in the challenge, submitting a total of 22 systems, obtaining very promising results.

This paper presents the findings of the third iteration of the AmericasNLP Shared Task on Machine Translation. This year’s competition features eleven Indigenous languages found across North, Central, and South America. A total of six teams participate with a total of 157 submissions across all languages and models. Two baselines – the Sheffield and Helsinki systems from 2023 – are provided and represent hard-to-beat starting points for the competition. In addition to the baselines, teams are given access to a new repository of training data which consists of data collected by teams in prior shared tasks. Using ChrF++ as the main competition metric, we see improvements over the baseline for 4 languages: Chatino, Guarani, Quechua, and Rarámuri, with performance increases over the best baseline of 4.2 ChrF++. In this work, we present a summary of the submitted systems, results, and a human evaluation of system outputs for Bribri, which consists of both (1) a rating of meaning and fluency and (2) a qualitative error analysis of outputs from the best submitted system.

In this work, we present the results of the AmericasNLP 2023 Shared Task on Machine Translation into Indigenous Languages of the Americas. This edition of the shared task featured eleven language pairs, one of which – Chatino-Spanish – uses a newly collected evaluation dataset, consisting of professionally translated text from the legal domain. Seven teams participated in the shared task, with a total of 181 submissions. Additionally, we conduct a human evaluation of the best system outputs, and compare them to the best submissions from the prior shared task. We find that this analysis agrees with the quantitative measures used to rank submissions, which shows further improvements of 9.64 ChrF on average across all languages, when compared to the prior winning system.

Large multilingual models have inspired a new class of word alignment methods, which work well for the model’s pretraining languages. However, the languages most in need of automatic alignment are low-resource and, thus, not typically included in the pretraining data. In this work, we ask: How do modern aligners perform on unseen languages, and are they better than traditional methods? We contribute gold-standard alignments for Bribri–Spanish, Guarani–Spanish, Quechua–Spanish, and Shipibo-Konibo–Spanish. With these, we evaluate state-of-the-art aligners with and without model adaptation to the target language. Finally, we also evaluate the resulting alignments extrinsically through two downstream tasks: named entity recognition and part-of-speech tagging. We find that although transformer-based methods generally outperform traditional models, the two classes of approach remain competitive with each other.

Syntactic probing methods have been used to examine whether and how pre-trained language models (PLMs) encode syntactic features. However, the probing methods are usually biased by the PLMs’ memorization of common word co-occurrences, even if they do not form syntactic relations. This paper presents a random-word-substitution and random-label-matching control task to reduce these biases and improve the robustness of syntactic probing methods. Our control tasks are also shown to notably improve the consistency of probing results between different probing methods and make the methods more robust with respect to the text attributes of the probing instances. Our control tasks make syntactic probing methods better at reconstructing syntactic features and more generalizable to unseen text domains. Our experiments show that our proposed control tasks are effective on different PLMs, probing methods, and syntactic features.

Pretrained multilingual models are able to perform cross-lingual transfer in a zero-shot setting, even for languages unseen during pretraining. However, prior work evaluating performance on unseen languages has largely been limited to low-level, syntactic tasks, and it remains unclear if zero-shot learning of high-level, semantic tasks is possible for unseen languages. To explore this question, we present AmericasNLI, an extension of XNLI (Conneau et al., 2018) to 10 Indigenous languages of the Americas. We conduct experiments with XLM-R, testing multiple zero-shot and translation-based approaches. Additionally, we explore model adaptation via continued pretraining and provide an analysis of the dataset by considering hypothesis-only models. We find that XLM-R’s zero-shot performance is poor for all 10 languages, with an average performance of 38.48%. Continued pretraining offers improvements, with an average accuracy of 43.85%. Surprisingly, training on poorly translated data by far outperforms all other methods with an accuracy of 49.12%.

This paper describes the process of data processing and training of an automatic speech recognition (ASR) system for Cook Islands Māori (CIM), an Indigenous language spoken by approximately 22,000 people in the South Pacific. We transcribed four hours of speech from adults and elderly speakers of the language and prepared two experiments. First, we trained three ASR systems: one statistical, Kaldi; and two based on Deep Learning, DeepSpeech and XLSR-Wav2Vec2. Wav2Vec2 tied with Kaldi for lowest character error rate (CER=6±1) and was slightly behind in word error rate (WER=23±2 versus WER=18±2 for Kaldi). This provides evidence that Deep Learning ASR systems are reaching the performance of statistical methods on small datasets, and that they can work effectively with extremely low-resource Indigenous languages like CIM. In the second experiment we used Wav2Vec2 to train models with held-out speakers. While the performance decreased (CER=15±7, WER=46±16), the system still showed considerable learning. We intend to use ASR to accelerate the documentation of CIM, using newly transcribed texts to improve the ASR and also generate teaching and language revitalization materials. The trained model is available under a license based on the Kaitiakitanga License, which provides for non-commercial use while retaining control of the model by the Indigenous community.

Word embeddings are critical for numerous NLP tasks but their evaluation in actual under-resourced settings needs further examination. This paper presents a case study in Bribri, a Chibchan language from Costa Rica. Four experiments were adapted from English: Word similarities, WordSim353 correlations, odd-one-out tasks and analogies. Here we discuss their adaptation to an under-resourced Indigenous language and we use them to measure semantic and morphological learning. We trained 96 word2vec models with different hyperparameter combinations. The best models for this under-resourced scenario were Skip-grams with an intermediate size (100 dimensions) and large window sizes (10). These had an average correlation of r=0.28 with WordSim353, a 76% accuracy in semantic odd-one-out and 70% accuracy in structural/morphological odd-one-out. The performance was lower for the analogies: The best models could find the appropriate semantic target amongst the first 25 results approximately 60% of the times, but could only find the morphological/structural target 11% of the times. Future research needs to further explore the patterns of morphological/structural learning, to examine the behavior of deep learning embeddings, and to establish a human baseline. This project seeks to improve Bribri NLP and ultimately help in its maintenance and revitalization.

Linguistic tone is transcribed for input into ASR systems in numerous ways. This paper shows a systematic test of several transcription styles, using as an example the Chibchan language Bribri, an extremely low-resource language from Costa Rica. The most successful models separate the tone from the vowel, so that the ASR algorithms learn tone patterns independently. These models showed improvements ranging from 4% to 25% in character error rate (CER), and between 3% and 23% in word error rate (WER). This is true for both traditional GMM/HMM and end-to-end CTC algorithms. This paper also presents the first attempt to train ASR models for Bribri. The best performing models had a CER of 33% and a WER of 50%. Despite the disadvantage of using hand-engineered representations, these models were trained on only 68 minutes of data, and therefore show the potential of ASR to generate further training materials and aid in the documentation and revitalization of the language.

This paper presents the results of the 2021 Shared Task on Open Machine Translation for Indigenous Languages of the Americas. The shared task featured two independent tracks, and participants submitted machine translation systems for up to 10 indigenous languages. Overall, 8 teams participated with a total of 214 submissions. We provided training sets consisting of data collected from various sources, as well as manually translated sentences for the development and test sets. An official baseline trained on this data was also provided. Team submissions featured a variety of architectures, including both statistical and neural models, and for the majority of languages, many teams were able to considerably improve over the baseline. The best performing systems achieved 12.97 ChrF higher than baseline, when averaged across languages.

This paper presents a neural machine translation model and dataset for the Chibchan language Bribri, with an average performance of BLEU 16.9±1.7. This was trained on an extremely small dataset (5923 Bribri-Spanish pairs), providing evidence for the applicability of NMT in extremely low-resource environments. We discuss the challenges entailed in managing training input from languages without standard orthographies, we provide evidence of successful learning of Bribri grammar, and also examine the translations of structures that are infrequent in major Indo-European languages, such as positional verbs, ergative markers, numerical classifiers and complex demonstrative systems. In addition to this, we perform an experiment of augmenting the dataset through iterative back-translation (Sennrich et al., 2016a; Hoang et al., 2018) by using Spanish sentences to create synthetic Bribri sentences. This improves the score by an average of 1.0 BLEU, but only when the new Spanish sentences belong to the same domain as the other Spanish examples. This contributes to the small but growing body of research on Chibchan NLP.

This paper presents three ongoing projects for NLP in Cook Islands Maori: Untrained Forced Alignment (approx. 9% error when detecting the center of words), speech-to-text (37% WER in the best trained models) and POS tagging (92% accuracy for the best performing model). Included as part of these projects are new resources filling in a gap in Australasian languages, including gold standard POS-tagged written corpora, transcribed speech corpora, time-aligned corpora down to the level of phonemes. These are part of efforts to accelerate the documentation of Cook Islands Maori and to increase its vitality amongst its users.