From Priest to Doctor: Domain Adaptaion for Low-Resource Neural Machine Translation

Many of the world's languages have insufficient data to train high-performing general neural machine translation (NMT) models, let alone domain-specific models, and often the only available parallel data are small amounts of religious texts. Hence, domain adaptation (DA) is a crucial issue faced by contemporary NMT and has, so far, been underexplored for low-resource languages. In this paper, we evaluate a set of methods from both low-resource NMT and DA in a realistic setting, in which we aim to translate between a high-resource and a low-resource language with access to only: a) parallel Bible data, b) a bilingual dictionary, and c) a monolingual target-domain corpus in the high-resource language. Our results show that the effectiveness of the tested methods varies, with the simplest one, DALI, being most effective. We follow up with a small human evaluation of DALI, which shows that there is still a need for more careful investigation of how to accomplish DA for low-resource NMT.

Boosting the Capabilities of Compact Models in Low-Data Contexts with Large Language Models and Retrieval-Augmented Generation

The data and compute requirements of current language modeling technology pose challenges for the processing and analysis of low-resource languages. Declarative linguistic knowledge has the potential to partially bridge this data scarcity gap by providing models with useful inductive bias in the form of language-specific rules. In this paper, we propose a retrieval augmented generation (RAG) framework backed by a large language model (LLM) to correct the output of a smaller model for the linguistic task of morphological glossing. We leverage linguistic information to make up for the lack of data and trainable parameters, while allowing for inputs from written descriptive grammars interpreted and distilled through an LLM. The results demonstrate that significant leaps in performance and efficiency are possible with the right combination of: a) linguistic inputs in the form of grammars, b) the interpretive power of LLMs, and c) the trainability of smaller token classification networks. We show that a compact, RAG-supported model is highly effective in data-scarce settings, achieving a new state-of-the-art for this task and our target languages. Our work also offers documentary linguists a more reliable and more usable tool for morphological glossing by providing well-reasoned explanations and confidence scores for each output.

Can we teach language models to gloss endangered languages?

Interlinear glossed text (IGT) is a popular format in language documentation projects, where each morpheme is labeled with a descriptive annotation. Automating the creation of interlinear glossed text can be desirable to reduce annotator effort and maintain consistency across annotated corpora. Prior research has explored a number of statistical and neural methods for automatically producing IGT. As large language models (LLMs) have showed promising results across multilingual tasks, even for rare, endangered languages, it is natural to wonder whether they can be utilized for the task of generating IGT. We explore whether LLMs can be effective at the task of interlinear glossing with in-context learning, without any traditional training. We propose new approaches for selecting examples to provide in-context, observing that targeted selection can significantly improve performance. We find that LLM-based methods beat standard transformer baselines, despite requiring no training at all. These approaches still underperform state-of-the-art supervised systems for the task, but are highly practical for researchers outside of the NLP community, requiring minimal effort to use.

TAMS: Translation-Assisted Morphological Segmentation

Canonical morphological segmentation is the process of analyzing words into the standard (aka underlying) forms of their constituent morphemes. This is a core task in language documentation, and NLP systems have the potential to dramatically speed up this process. But in typical language documentation settings, training data for canonical morpheme segmentation is scarce, making it difficult to train high quality models. However, translation data is often much more abundant, and, in this work, we present a method that attempts to leverage this data in the canonical segmentation task. We propose a character-level sequence-to-sequence model that incorporates representations of translations obtained from pretrained high-resource monolingual language models as an additional signal. Our model outperforms the baseline in a super-low resource setting but yields mixed results on training splits with more data. While further work is needed to make translations useful in higher-resource settings, our model shows promise in severely resource-constrained settings.

GlossLM: Multilingual Pretraining for Low-Resource Interlinear Glossing

A key aspect of language documentation is the creation of annotated text in a format such as interlinear glossed text (IGT), which captures fine-grained morphosyntactic analyses in a morpheme-by-morpheme format. Prior work has explored methods to automatically generate IGT in order to reduce the time cost of language analysis. However, many languages (particularly those requiring preservation) lack sufficient IGT data to train effective models, and crosslingual transfer has been proposed as a method to overcome this limitation. We compile the largest existing corpus of IGT data from a variety of sources, covering over 450k examples across 1.8k languages, to enable research on crosslingual transfer and IGT generation. Then, we pretrain a large multilingual model on a portion of this corpus, and further finetune it to specific languages. Our model is competitive with state-of-the-art methods for segmented data and large monolingual datasets. Meanwhile, our model outperforms SOTA models on unsegmented text and small corpora by up to 6.6% morpheme accuracy, demonstrating the effectiveness of crosslingual transfer for low-resource languages.

Robust Generalization Strategies for Morpheme Glossing in an Endangered Language Documentation Context

Generalization is of particular importance in resource-constrained settings, where the available training data may represent only a small fraction of the distribution of possible texts. We investigate the ability of morpheme labeling models to generalize by evaluating their performance on unseen genres of text, and we experiment with strategies for closing the gap between performance on in-distribution and out-of-distribution data. Specifically, we use weight decay optimization, output denoising, and iterative pseudo-labeling, and achieve a 2% improvement on a test set containing texts from unseen genres. All experiments are performed using texts written in the Mayan language Uspanteko.

Taxonomic Loss for Morphological Glossing of Low-Resource Languages

Morpheme glossing is a critical task in automated language documentation and can benefit other downstream applications greatly. While state-of-the-art glossing systems perform very well for languages with large amounts of existing data, it is more difficult to create useful models for low-resource languages. In this paper, we propose the use of a taxonomic loss function that exploits morphological information to make morphological glossing more performant when data is scarce. We find that while the use of this loss function does not outperform a standard loss function with regards to single-label prediction accuracy, it produces better predictions when considering the top-n predicted labels. We suggest this property makes the taxonomic loss function useful in a human-in-the-loop annotation setting.

System Demo: Tool and Infrastructure for Offensive Language Error Analysis (OLEA) in English

The automatic detection of offensive language is a pressing societal need. Many systems perform well on explicit offensive language but struggle to detect more complex, nuanced, or implicit cases of offensive and hateful language. OLEA is an open-source Python library that provides easy-to-use tools for error analysis in the context of detecting offensive language in English. OLEA also provides an infrastructure for re-distribution of new datasets and analysis methods requiring very little coding.

A Kind Introduction to Lexical and Grammatical Aspect, with a Survey of Computational Approaches

Aspectual meaning refers to how the internal temporal structure of situations is presented. This includes whether a situation is described as a state or as an event, whether the situation is finished or ongoing, and whether it is viewed as a whole or with a focus on a particular phase. This survey gives an overview of computational approaches to modeling lexical and grammatical aspect along with intuitive explanations of the necessary linguistic concepts and terminology. In particular, we describe the concepts of stativity, telicity, habituality, perfective and imperfective, as well as influential inventories of eventuality and situation types. We argue that because aspect is a crucial component of semantics, especially when it comes to reporting the temporal structure of situations in a precise way, future NLP approaches need to be able to handle and evaluate it systematically in order to achieve human-level language understanding.

AmericasNLI: Evaluating Zero-shot Natural Language Understanding of Pretrained Multilingual Models in Truly Low-resource Languages

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 38.62%. Continued pretraining offers improvements, with an average accuracy of 44.05%. Surprisingly, training on poorly translated data by far outperforms all other methods with an accuracy of 48.72%.