Browsing Tesis de Master by Author "Hizkuntzaren Azterketa eta Prozesamendua Unibertsitate Masterra"
Now showing items 1-12 of 12
-
Basque and Spanish Counter Narrative Generation: Data Creation and Evaluation
Bengoetxea Azurmendi, Jaione (2023-06-30)Counter Narratives (CN) are responses to Hate Speech (HS), which include non-negative feedback as well as fact-bound arguments, with the aim of de-escalating potentially hateful debates. However, due to the growing presence ... -
Basque and Spanish Multilingual TTS Model for Speech-to-Speech Translation
De Zuazo Oteiza, Xabier (2023-06-30)[EN] Lately, multiple Text-to-Speech models have emerged using Deep Neural networks to synthesize audio from text. In this work, the state-of-the-art multilingual and multi-speaker Text-to-Speech model has been trained ... -
Does Coreference Resolution Improve Aspect Based Sentiment Analysis?
Ryhänen, Rosa-Maria Kristiina (2023-06-30)Aspect-Based Sentiment Analysis (ABSA) has generally focused on extracting explicit opinion targets and classifying them into polarities and categories. Most approaches ignore implicitly expressed opinions, even though ... -
Entailment for Zero- and Few-Shot Text Classification in Catalan: Monolingual vs. Multilingual Resources and Task Transfer
Baucells de la Peña, Irene (2023-06-30)As the field of NLP continues to evolve and expand in industry, new tasks and languages emerge for which task-specific data for fine-tuning is often scarce or unavailable. Against this background, zero- and few-shot ... -
Evaluation of STT technologies performance and database design for Spanish dysarthric speech
Madina González, Margot (2023-06-30)[EN] Automatic Speech Recognition (ASR) systems have become an everyday use tool worldwide. Their use has spread throughout these last years and they have also been implemented in Environmental Control Systems (ECS) or ... -
Few-shot Learning for Argumentation in the Medical Domain
Manzanal Martín, Jon (2023-06-30)[EU] Azkenaldian, arlo medikoan arreta handiagoa jarri da Adimen Artifizialarekin lotutako tekniketan, medikuei galderak errazago eta azkarrago ebazten laguntzeko. Hori bereziki garrantzitsua da Ebidentzian Oinarritutako ... -
Grounding Language Models for Compositional and Spatial Reasoning
Etxaniz Aragoneses, Julen (2023-06-30)Humans can learn to understand and process the distribution of space, and one of the initial tasks of Artificial Intelligence has been to show machines the relationships between space and the objects that appear in it. ... -
Hizkuntza-arteko distilazioa eta antzekotasun semantikoa maiz egiten diren galderak erantzuteko
Berrondo Urruzola, Ander (2023-06-30)Azken urteotan gure artean egon den COVID-19aren harira, gaixotasunari buruzko dudak argitzeko sistema bat garatu nahi izan da, Osakidetzak eskainitako Maiz Eginiko Galderen (MEG) multzo batean oinarrituta; honela, sistemaren ... -
Labour Statistics vs. Static Word Embeddings: a Comparison of Gender Bias
Figueroa Vásquez, Andrés (2023-06-30)This project explores the relation between labour statistics information and three language models: GloVe, word2vec and fastText, in both English and Spanish. The aim is to see what differs in reality versus word embedding ... -
Natural Language Inference Models for Few-Shot Text Classification: A Real-World Perspective
Romero Mogrovejo, David Orlando (2023-06-30)[EN] Pivoting tasks as entailment problems have shown to be very effective in different applications like question answering and relation extraction. On the other hand, language models trained for entailment tasks have ... -
Politeness control as a domain adaptation problem in NMT: fine-tuning vs. multi-register models for Castilian Spanish
Soler Uguet, Celia (2023-06-30)(EN) Given that Neural Machine Translation (NMT) systems have been proven to generate translations with a quality that is being regarded as close to that of a human, we believe it is the time to start paying attention to ... -
Unsupervised information retrieval using large language models
Domínguez Becerril, Carlos (2023-06-30)Nowadays, to tackle the open domain Question Answering (QA) problem, a neural architecture with two main components is usually used: the information retriever, whose task is to search for the most relevant documents with ...