Browsing Máster Universitario en Análisis y Procesamiento del Lenguaje by Issue Date
Now showing items 41-60 of 61
-
Exploration of aunnotation strategies for entailment-based Automatic Short Answer Grading
(2023-06-30)[EN] Recent work has shown that Automatic Short Answer Grading can effectively be reformulated as a Textual Entailment problem. In this work we show that this reformulation is also effective in zero-shot and few-shot ... -
Data Augmentation to Low-Resource Languages Approach: Galician case
(2023-06-30)In this Final Thesis, two proposals for data augmentation have been made for the training of two bilingual translation models in Spanish-Galician and English-Galician from parallel corpora of Portuguese. One of the ... -
GLEN: Adiera desanbiguazioa hizkuntza-eredu sortzaileak erabiliz
(2023-06-30)Azken urteotako ikasketa sakonean oinarritutako sistema sortzaileek ospea lortu dute jendartean gizakien idazkera naturala imitatzeko ahalmenak bultzatuta. Honez gain, hizkuntzaren prozesamenduko hainbat atazetan emaitza ... -
Unsupervised information retrieval using large language models
(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 ... -
Few-shot Learning for Argumentation in the Medical Domain
(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 ... -
Basque and Spanish Multilingual TTS Model for Speech-to-Speech Translation
(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 ... -
Entailment for Zero- and Few-Shot Text Classification in Catalan: Monolingual vs. Multilingual Resources and Task Transfer
(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 ... -
Natural Language Inference Models for Few-Shot Text Classification: A Real-World Perspective
(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 ... -
Does Coreference Resolution Improve Aspect Based Sentiment Analysis?
(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 ... -
Analysis of user post-edited texts and a proposal for assistance through iSTS
(2023-06-30)In the present investigation, the way lay users employ machine translation (MT) systems has been studied. The benefits of applying these systems for the dissemination have been examined to limit the scope, and the ... -
Labour Statistics vs. Static Word Embeddings: a Comparison of Gender Bias
(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 ... -
Study of a Metric for Measuring Gender Bias in BERT Language Models
(2023-06-30)[EN] Since the creation of language models such as BERT, they are being deployed widely as services on platforms to serve millions of users. With their increasing popularity, the fairness of NLP systems and algorithms is ... -
Error Generation for a Grammar Checker in Basque: Correction and Detection
(2023-06-30)This work presents a method for automatic generation of grammatically incorrect sentences, which can later be used for training Neural Grammar Error Correction and Detection models. The quality of the generated synthetic ... -
Hizkuntza-arteko distilazioa eta antzekotasun semantikoa maiz egiten diren galderak erantzuteko
(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 ... -
Grounding Language Models for Compositional and Spatial Reasoning
(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. ... -
Prototyping a chatbot for practising conversational English with corrective feedback
(2023-06-30)This work focuses on chatbots’ application in the educational domain, and precisely, in the area of foreign language learning. The goal of this project is to create a prototype of a chatbot that aims at improving learners’ ... -
Genial...: Automatic Irony Detection in Spanish Tweets
(2023-06-30)Irony is a form of non-literal speech that can alter the meaning of an utterance. Understanding irony may greatly impact Natural Language Processing (NLP) tasks such as sentiment analysis or stance detection. While a ... -
Evaluation of STT technologies performance and database design for Spanish dysarthric speech
(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 ... -
Analysing specialized use of verbs: the case of some Catalan trajectory verbs in the sport domain
(2023-06-30)[EN]This master thesis presents a syntactic-semantic analysis of 5 Catalan verbs of trajectory class (aconseguir (to achieve), arribar (to arrive), avan ̧car (to move forward), entrar (to enter) and sortir (to come out)) ... -
Politeness control as a domain adaptation problem in NMT: fine-tuning vs. multi-register models for Castilian Spanish
(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 ...