Related papers: Multilingual textual data: an approach through mul…
Morphological inflection is a popular task in sub-word NLP with both practical and cognitive applications. For years now, state-of-the-art systems have reported high, but also highly variable, performance across data sets and languages. We…
Network models are powerful tools for gaining new insights from complex biological data. Most lines of investigation in biology involve comparing datasets in the setting where the same predictors are measured across multiple studies or…
Large language models (LLMs) achieve impressive results in terms of fluency in text generation, yet the nature of their linguistic knowledge - in particular the human-likeness of their internal lexicon - remains uncertain. This study…
For multilingual factual knowledge assessment of LLMs, benchmarks such as MLAMA use template translations that do not take into account the grammatical and semantic information of the named entities inserted in the sentence. This leads to…
Multilingual language models have gained significant attention in recent years, enabling the development of applications that meet diverse linguistic contexts. In this paper, we present a comprehensive evaluation of three popular…
While language is a complex adaptive system, most work on syntactic variation observes a few individual constructions in isolation from the rest of the grammar. This means that the grammar, a network which connects thousands of structures…
Recently, significant public efforts have been directed towards developing low-cost models with capabilities akin to ChatGPT, thereby fostering the growth of open-source conversational models. However, there remains a scarcity of…
One of the most widely used tasks for evaluating Large Language Models (LLMs) is Multiple-Choice Question Answering (MCQA). While open-ended question answering tasks are more challenging to evaluate, MCQA tasks are, in principle, easier to…
Emerging digital technologies are exacerbating the existing divide in Open Access Data (OAD) between high-and low-resource languages, excluding many communities from participating in the global digital transformation. In this PhD proposal,…
Large Language Models (LLMs) are increasingly used to answer everyday questions, yet their performance on culturally grounded and dialectal content remains uneven across languages. We propose a comprehensive method that (i) translates…
Existing work in document-level neural machine translation commonly concatenates several consecutive sentences as a pseudo-document, and then learns inter-sentential dependencies. This strategy limits the model's ability to leverage…
Computational models of emergent communication in agent populations are currently gaining interest in the machine learning community due to recent advances in Multi-Agent Reinforcement Learning (MARL). Current contributions are however…
The table reasoning task aims to answer the question according to the given table. Currently, using Large Language Models (LLMs) is the predominant method for table reasoning. Most existing methods employ a fixed tabular format to represent…
The exploration of multimodal language models integrates multiple data types, such as images, text, language, audio, and other heterogeneity. While the latest large language models excel in text-based tasks, they often struggle to…
Video question answering has recently received a lot of attention from multimodal video researchers. Most video question answering datasets are usually in the form of multiple-choice. But, the model for the multiple-choice task does not…
Cultural biases in multilingual datasets pose significant challenges for their effectiveness as global benchmarks. These biases stem not only from differences in language but also from the cultural knowledge required to interpret questions,…
Meta-learning has been shown to have better performance than supervised learning for few-shot monolingual spoken word classification. However, the meta-learning approach remains under-explored in multilingual spoken word classification. In…
This paper presents LOLA, a massively multilingual large language model trained on more than 160 languages using a sparse Mixture-of-Experts Transformer architecture. Our architectural and implementation choices address the challenge of…
Multimodal large language models (MLLMs) enhance the capabilities of standard large language models by integrating and processing data from multiple modalities, including text, vision, audio, video, and 3D environments. Data plays a pivotal…
Automated predictions require explanations to be interpretable by humans. Past work used attention and rationale mechanisms to find words that predict the target variable of a document. Often though, they result in a tradeoff between noisy…