Related papers: Experiments with Universal CEFR Classification

Closely related languages show linguistic similarities that allow speakers of one language to understand speakers of another language without having actively learned it. Mutual intelligibility varies in degree and is typically tested in…

We present UDify, a multilingual multi-task model capable of accurately predicting universal part-of-speech, morphological features, lemmas, and dependency trees simultaneously for all 124 Universal Dependencies treebanks across 75…

Speech classification has attracted increasing attention due to its wide applications, particularly in classifying physical and mental states. However, these tasks are challenging due to the high variability in speech signals. Ensemble…

Language development experts need tools that can automatically identify languages from fluent, conversational speech, and provide reliable estimates of usage rates at the level of an individual recording. However, language identification…

We present a compact, single-model approach to multilingual inflection, the task of generating inflected word forms from base lemmas to express grammatical categories. Our model, trained jointly on data from 73 languages, is lightweight,…

Most languages of the world pose low-resource challenges to natural language processing models. With multilingual training, knowledge can be shared among languages. However, not all languages positively influence each other and it is an…

Multilingual Automatic Speech Recognition (ASR) models have extended the usability of speech technologies to a wide variety of languages. With how many languages these models have to handle, however, a key to understanding their imbalanced…

In cross-lingual language models, representations for many different languages live in the same space. Here, we investigate the linguistic and non-linguistic factors affecting sentence-level alignment in cross-lingual pretrained language…

Synthetic datasets constructed from formal languages allow fine-grained examination of the learning and generalization capabilities of machine learning systems for sequence classification. This article presents a new benchmark for machine…

Curriculum Learning is a powerful training method that allows for faster and better training in some settings. This method, however, requires having a notion of which examples are difficult and which are easy, which is not always trivial to…

This paper tests the hypothesis that distinctive feature classifiers anchored at phonetic landmarks can be transferred cross-lingually without loss of accuracy. Three consonant voicing classifiers were developed: (1) manually selected…

We introduce polyglot language models, recurrent neural network models trained to predict symbol sequences in many different languages using shared representations of symbols and conditioning on typological information about the language to…

Machine hearing or listening represents an emerging area. Conventional approaches rely on the design of handcrafted features specialized to a specific audio task and that can hardly generalized to other audio fields. For example,…

Complex Word Identification (CWI) is a task centered on detecting hard-to-understand words, or groups of words, in texts from different areas of expertise. The purpose of CWI is to highlight problematic structures that non-native speakers…

Large language models (LLMs) have exhibited considerable cross-lingual generalization abilities, whereby they implicitly transfer knowledge across languages. However, the transfer is not equally successful for all languages, especially for…

Pretrained multilingual language models can help bridge the digital language divide, enabling high-quality NLP models for lower resourced languages. Studies of multilingual models have so far focused on performance, consistency, and…

Despite the fact that different objects possess distinct class-specific features, they also usually share common patterns. Inspired by this observation, we propose a novel method to explicitly and simultaneously learn a set of common…

Large language models (LLMs) provide detailed and impressive responses to queries in English. However, are they really consistent at responding to the same query in other languages? The popular way of evaluating for multilingual performance…

While preliminary findings indicate that multilingual LLMs exhibit reduced bias compared to monolingual ones, a comprehensive understanding of the effect of multilingual training on bias mitigation, is lacking. This study addresses this gap…

Why do some languages like Czech permit free word order, while others like English do not? We address this question by pretraining transformer language models on a spectrum of synthetic word-order variants of natural languages. We observe…