Related papers: Experiments with Universal CEFR Classification

Word segmentation is a low-level NLP task that is non-trivial for a considerable number of languages. In this paper, we present a sequence tagging framework and apply it to word segmentation for a wide range of languages with different…

This paper presents a language-independent approach to controlled vocabulary keyword assignment using the EUROVOC thesaurus. Due to the multilingual nature of EUROVOC, the keywords for a document written in one language can be displayed in…

Realizing general-purpose language intelligence has been a longstanding goal for natural language processing, where standard evaluation benchmarks play a fundamental and guiding role. We argue that for general-purpose language intelligence…

BERT and other large-scale language models (LMs) contain gender and racial bias. They also exhibit other dimensions of social bias, most of which have not been studied in depth, and some of which vary depending on the language. In this…

Multilingual Large Language Models (LLMs) develop cross-lingual abilities despite being trained on limited parallel data. However, they often struggle to generate responses in the intended language, favoring high-resource languages such as…

System prompts provide a lightweight yet powerful mechanism for conditioning large language models (LLMs) at inference time. While prior work has focused on English-only settings, real-world deployments benefit from having a single prompt…

The number of end-to-end speech recognition models grows every year. These models are often adapted to new domains or languages resulting in a proliferation of expert systems that achieve great results on target data, while generally…

Emotion classification in multilingual settings remains constrained by the scarcity of annotated data: existing corpora are predominantly English, single-label, and cover few languages. We address this gap by constructing a large-scale…

We present the first comprehensive evaluation of cross-lingual unlearning in multilingual LLMs. Using translated TOFU benchmarks in seven language/script variants, we test major unlearning algorithms and show that most fail to remove facts…

We present ONERULER, a multilingual benchmark designed to evaluate long-context language models across 26 languages. ONERULER adapts the English-only RULER benchmark (Hsieh et al., 2024) by including seven synthetic tasks that test both…

Large language models (LLMs) operate in two fundamental learning modes - fine-tuning (FT) and in-context learning (ICL) - raising key questions about which mode yields greater language proficiency and whether they differ in their inductive…

During the past several years, a surge of multi-lingual Pre-trained Language Models (PLMs) has been proposed to achieve state-of-the-art performance in many cross-lingual downstream tasks. However, the understanding of why multi-lingual…

Multilingual automatic speech recognition (ASR) systems mostly benefit low resource languages but suffer degradation in performance across several languages relative to their monolingual counterparts. Limited studies have focused on…

Multi-pulse magnetic resonance imaging (MRI) is widely utilized for clinical practice such as Alzheimer's disease diagnosis. To train a robust model for multi-pulse MRI classification, it requires large and diverse data from various medical…

Neural language modeling (LM) has led to significant improvements in several applications, including Automatic Speech Recognition. However, they typically require large amounts of training data, which is not available for many domains and…

Acoustic word embeddings are fixed-dimensional representations of variable-length speech segments. Such embeddings can form the basis for speech search, indexing and discovery systems when conventional speech recognition is not possible. In…

The great majority of languages in the world are considered under-resourced for the successful application of deep learning methods. In this work, we propose a meta-learning approach to document classification in limited-resource setting…

With the increasing industrial relevance of quantum technologies (QTs), a new quantum workforce with special qualification will be needed. Building this workforce requires educational efforts, ranging from short term training to degree…

In this paper, we present a unified model that works for both multilingual and crosslingual prediction of reading times of words in various languages. The secret behind the success of this model is in the preprocessing step where all words…

Semantic role labeling (SRL) identifies predicate-argument structure(s) in a given sentence. Although different languages have different argument annotations, polyglot training, the idea of training one model on multiple languages, has…