GeoLingIt at EVALITA 2023: Overview of the geolocation of linguistic variation in Italy task

A Ramponi, C Casula - … of the Eighth Evaluation Campaign of …, 2024 - books.google.com
GeoLingIt is the first shared task on geolocation of linguistic variation in Italy from social
media posts comprising content in language varieties other than standard Italian (ie …

Malto at semeval-2024 task 6: Leveraging synthetic data for llm hallucination detection

F Borra, C Savelli, G Rosso, A Koudounas… - arxiv preprint arxiv …, 2024 - arxiv.org
In Natural Language Generation (NLG), contemporary Large Language Models (LLMs) face
several challenges, such as generating fluent yet inaccurate outputs and reliance on fluency …

Leveraging Contrastive Learning for Few-shot Geolocation of Social Posts

M Li, KH Lim - arxiv preprint arxiv:2403.00786, 2024 - arxiv.org
Social geolocation is an important problem of predicting the originating locations of social
media posts. However, this task is challenging due to the need for a substantial volume of …

FewUser: Few-Shot Social User Geolocation via Contrastive Learning

M Li, KH Lim - arxiv preprint arxiv:2404.08662, 2024 - arxiv.org
To address the challenges of scarcity in geotagged data for social user geolocation, we
propose FewUser, a novel framework for Few-shot social User geolocation. We incorporate …

Enhancing Cross-Lingual Word Embeddings: Aligned Subword Vectors for Out-of-Vocabulary Terms in fastText

C Savelli, F Giobergia - 2024 IEEE 18th International …, 2024 - ieeexplore.ieee.org
The word embedding models have significantly impacted Natural Language Processing,
particularly in multilingual settings. The well-known fastText approach proposed a …