https://www.um.edu.mt/library/oar/handle/123456789/13902 Sat, 24 Oct 2026 02:40:44 GMT 2026-10-24T02:40:44Z https://www.um.edu.mt/library/oar/handle/123456789/150139 Title: Can language models learn analogical reasoning? Investigating training objectives and comparisons to human performance Authors: Petersen, Molly R.; van der Plas, Lonneke Abstract: While analogies are a common way to evaluate word embeddings in NLP, it is also of interest to investigate whether or not analogical reasoning is a task in itself that can be learned. In this paper, we test several ways to learn basic analogical reasoning, specifically focusing on analogies that are more typical of what is used to evaluate analogical reasoning in humans than those in commonly used NLP benchmarks. Our experiments find that models are able to learn analogical reasoning, even with a small amount of data. We additionally compare our models to a dataset with a human baseline, and find that after training, models approach human performance. Fri, 01 Dec 2023 00:00:00 GMT https://www.um.edu.mt/library/oar/handle/123456789/150139 2023-12-01T00:00:00Z https://www.um.edu.mt/library/oar/handle/123456789/150062 Title: Cross-lingual transfer learning with Persian Authors: Mollanorozy, Sepideh; Tanti, Marc; Nissim, Malvina Abstract: The success of cross-lingual transfer learning for POS tagging has been shown to be strongly dependent, among other factors, on the (typological and/or genetic) similarity of the lowresource language used for testing and the language( s) used in pre-training or to fine-tune the model. We further unpack this finding in two directions by zooming in on a single language, namely Persian. First, still focusing on POS tagging we run an in-depth analysis of the behaviour of Persian with respect to closely related languages and languages that appear to benefit from cross-lingual transfer with Persian. To do so, we also use the World Atlas of Language Structures to determine which properties are shared between Persian and other languages included in the experiments. Based on our results, Persian seems to be a reasonable potential language for Kurmanji and Tagalog low-resource languages for other tasks as well. Second, we test whether previous findings also hold on a task other than POS tagging to pull apart the benefit of language similarity and the specific task for which such benefit has been shown to hold. We gather sentiment analysis datasets for 31 target languages and through a series of cross-lingual experiments analyse which languages most benefit from Persian as the source. The set of languages that benefit from Persian had very little overlap across the two tasks, suggesting a strong task-dependent component in the usefulness of language similarity in cross-lingual transfer. Mon, 01 May 2023 00:00:00 GMT https://www.um.edu.mt/library/oar/handle/123456789/150062 2023-05-01T00:00:00Z https://www.um.edu.mt/library/oar/handle/123456789/147895 Title: Rooted in the Mediterranean studies in Arabic dialectology Authors: Fabri, Ray; Gatt, Kurstin; Spagnol, Michael Abstract: This volume presents the proceedings of the 15th Conference of the International Association of Arabic Dialectology (AIDA) held at the Valletta Campus of the University of Malta from 21 to 24 May 2024. The conference was jointly organised by the Department of Maltese, the Department of Middle Eastern and Asian Languages and Cultures, and the Institute of Linguistics and Language Technology at the University of Malta. [excerpt] Mon, 01 Jan 2024 00:00:00 GMT https://www.um.edu.mt/library/oar/handle/123456789/147895 2024-01-01T00:00:00Z https://www.um.edu.mt/library/oar/handle/123456789/145885 Title: How to write up interdisciplinary research in line with its theoretical underpinnings Authors: Schembri, Natalie Abstract: This guide aims to equip readers with practical advice on how to write up an interdisciplinary study in line with the theoretical underpinnings of interdisciplinary research. It will focus on how to write your text, explaining areas where it is important to highlight the interdisciplinary nature of your study. There are critical points in an IMRAD (Introduction, Methodology, Results, and Discussion) structure where this must be justified, highlighted, and brought to bear on your research problem. This guide will provide examples from relevant published research to illustrate how you can do this. It will also give you a basic understanding of the theory behind these textual practices. Wed, 01 Jan 2025 00:00:00 GMT https://www.um.edu.mt/library/oar/handle/123456789/145885 2025-01-01T00:00:00Z