Efforts towards better machine translation (MT) for Creole languages have historically been isolated, due to Creole languages’ geographic and linguistic diversity. However, most speakers of Creole languages stand to benefit from improved MT for low-resource languages. To galvanize collaboration for Creole MT across the NLP community, we introduce the First Shared Task for Creole Language Machine Translation at WMT25. This Shared Task consists of two systems tracks and one data track, for which we received submissions from five participating teams. Participants experimented with a wide variety of systems development techniques. Our evaluation campaign gave rise to improvements in MT performance in several languages, and particularly large improvements in new testing genres, though some participants found that reusing subsets of pretraining data for specialized post-training did not yield significant improvements. Our campaign also yielded new test sets for Mauritian Creole and a vast expansion of public training data for two Creole languages of Latin America.

This document details the Johns Hopkins University’s submission to the 2025 WMT Shared Task for Creole Language Translation. We submitted exclusively to the data subtask, contributing machine translation bitext corpora for Belizean Kriol with English translations, and French Guianese Creole with French translations. These datasets contain 5,530 and 1,671 parallel lines of text, respectively, thus amounting to an 2,300% increase in publicly available lines of bitext for Belizean Creole with English, and an 370% such increase for French Guianese Creole with French. Experiments demonstrate genre-dependent improvements on our proposed test sets when the relevant state-of-the-art model is fine-tuned on our proposed train sets, with improvements across genres of up to 33.3 chrF++.

Thousands of the world’s languages are in danger of extinction—a tremendous threat to cultural identities and human language diversity. Interlinear Glossed Text (IGT) is a form of linguistic annotation that can support documentation and resource creation for these languages’ communities. IGT typically consists of (1) transcriptions, (2) morphological segmentation, (3) glosses, and (4) free translations to a majority language. We propose Wav2Gloss: a task in which these four annotation components are extracted automatically from speech, and introduce the first dataset to this end, Fieldwork: a corpus of speech with all these annotations, derived from the work of field linguists, covering 37 languages, with standard formatting, and train/dev/test splits. We provide various baselines to lay the groundwork for future research on IGT generation from speech, such as end-to-end versus cascaded, monolingual versus multilingual, and single-task versus multi-task approaches.

Conversational speech translation is an important technology that fosters communication among people of different language backgrounds. Three-way parallel data in the form of source speech, source transcript, and target translation is usually required to train end-to-end systems. However, such datasets are not readily available and are expensive to create as this involves multiple annotation stages. In this paper, we investigate the use of synthetic data from generative models, namely machine translation and text-to-speech synthesis, for training conversational speech translation systems. We show that adding synthetic data to the training recipe increasingly improves end-to-end training performance, especially when limited real data is available. However, when no real data is available, no amount of synthetic data helps.

A majority of language technologies are tailored for a small number of high-resource languages, while relatively many low-resource languages are neglected. One such group, Creole languages, have long been marginalized in academic study, though their speakers could benefit from machine translation (MT). These languages are predominantly used in much of Latin America, Africa and the Caribbean. We present the largest cumulative dataset to date for Creole language MT, including 14.5M unique Creole sentences with parallel translations—11.6M of which we release publicly, and the largest bitexts gathered to date for 41 languages—the first ever for 21. In addition, we provide MT models supporting all 41 Creole languages in 172 translation directions. Given our diverse dataset, we produce a model for Creole language MT exposed to more genre diversity then ever before, which outperforms a genre-specific Creole MT model on its own benchmark for 23 of 34 translation directions.

We describe a set of new methods to partially automate linguistic phylogenetic inference given (1) cognate sets with their respective protoforms and sound laws, (2) a mapping from phones to their articulatory features and (3) a typological database of sound changes.We train a neural network on these sound change data to weight articulatory distances between phones and predict intermediate sound change steps between historical protoforms and their modern descendants, replacing a linguistic expert in part of a parsimony-based phylogenetic inference algorithm. In our best experiments on Tukanoan languages, this method produces trees with a Generalized Quartet Distance of 0.12 from a tree that used expert annotations, a significant improvement over other semi-automated baselines. We discuss potential benefits and drawbacks to our neural approach and parsimony-based tree prediction. We also experiment with a minimal generalization learner for automatic sound law induction, finding it less effective than sound laws from expert annotation. Our code is publicly available.

Interlinear glossing provides a vital type of morphosyntactic annotation, both for linguists and language revitalists, and numerous conventions exist for representing it formally and computationally. Some of these formats are human readable; others are machine readable. Some are easy to edit with general-purpose tools. Few represent non-concatentative processes like infixation, reduplication, mutation, truncation, and tonal overwriting in a consistent and formally rigorous way (on par with affixation). We propose an annotation convention—Generalized Glossing Guidelines (GGG) that combines all of these positive properties using an Item-and-Process (IP) framework. We describe the format, demonstrate its linguistic adequacy, and compare it with two other interlinear glossed text annotation schemes.

In our submission to the SIGMORPHON 2023 Shared Task on interlinear glossing (IGT), we explore approaches to data augmentation and modeling across seven low-resource languages. For data augmentation, we explore two approaches: creating artificial data from the provided training data and utilizing existing IGT resources in other languages. On the modeling side, we test an enhanced version of the provided token classification baseline as well as a pretrained multilingual seq2seq model. Additionally, we apply post-correction using a dictionary for Gitksan, the language with the smallest amount of data. We find that our token classification models are the best performing, with the highest word-level accuracy for Arapaho and highest morpheme-level accuracy for Gitksan out of all submissions. We also show that data augmentation is an effective strategy, though applying artificial data pretraining has very different effects across both models tested.

Large language models (LLMs) implicitly learn to perform a range of language tasks, including machine translation (MT). Previous studies explore aspects of LLMs’ MT capabilities. However, there exist a wide variety of languages for which recent LLM MT performance has never before been evaluated. Without published experimental evidence on the matter, it is difficult for speakers of the world’s diverse languages to know how and whether they can use LLMs for their languages. We present the first experimental evidence for an expansive set of 204 languages, along with MT cost analysis, using the FLORES-200 benchmark. Trends reveal that GPT models approach or exceed traditional MT model performance for some high-resource languages (HRLs) but consistently lag for low-resource languages (LRLs), under-performing traditional MT for 84.1% of languages we covered. Our analysis reveals that a language’s resource level is the most important feature in determining ChatGPT’s relative ability to translate it, and suggests that ChatGPT is especially disadvantaged for LRLs and African languages.

Multilingual transfer techniques often improve low-resource machine translation (MT). Many of these techniques are applied without considering data characteristics. We show in the context of Haitian-to-English translation that transfer effectiveness is correlated with amount of training data and relationships between knowledge-sharing languages. Our experiments suggest that for some languages beyond a threshold of authentic data, back-translation augmentation methods are counterproductive, while cross-lingual transfer from a sufficiently related language is preferred. We complement this finding by contributing a rule-based French-Haitian orthographic and syntactic engine and a novel method for phonological embedding. When used with multilingual techniques, orthographic transformation makes statistically significant improvements over conventional methods. And in very low-resource Jamaican MT, code-switching with a transfer language for orthographic resemblance yields a 6.63 BLEU point advantage.

A variety of NLP applications use word2vec skip-gram, GloVe, and fastText word embeddings. These models learn two sets of embedding vectors, but most practitioners use only one of them, or alternately an unweighted sum of both. This is the first study to systematically explore a range of linear combinations between the first and second embedding sets. We evaluate these combinations on a set of six NLP benchmarks including IR, POS-tagging, and sentence similarity. We show that the default embedding combinations are often suboptimal and demonstrate 1.0-8.0% improvements. Notably, GloVes default unweighted sum is its least effective combination across tasks. We provide a theoretical basis for weighting one set of embeddings more than the other according to the algorithm and task. We apply our findings to improve accuracy in applications of cross-lingual alignment and navigational knowledge by up to 15.2%.