Biography

PhD Student in Language Analysis and Processing at Hitz Center IXA Group UPV/EHU. Working on Improving Language Models for Low-resource Languages. Graduate in Informatics Engineering with speciality in Software Engineering. Master in Language Analysis and Processing.

In this web you will find information about  Skills,  Certificates,  Projects,  Tags and  Contact.

Interests
  •  Programming
  •  Web Development
  •  Software Engineering
  •  Machine Learning
  •  Deep Learning
  •  Natural Language Processing
Education
  • Degree in Computer Engineering, 2017-2021

    University of the Basque Country (UPV/EHU)

  • Master in Language Analysis and Processing, 2021-2022

    University of the Basque Country (UPV/EHU)

  • PhD in Language Analysis and Processing, 2023-Present

    University of the Basque Country (UPV/EHU)

 Experience

 
 
 
 
 
UPV/EHU
PhD Student in Language Analysis and Processing
January 2023 – Present Donostia

 Education

 
 
 
 
 
UPV/EHU
Degree in Computer Engineering
September 2017 – September 2021 Donostia
 
 
 
 
 
UPV/EHU
Master in Language Analysis and Processing
October 2021 – October 2021 Donostia
 
 
 
 
 
UPV/EHU
PhD in Language Analysis and Processing
January 2023 – Present Donostia

 Languages

basque-country
Euskara
spain
Español
united-kingdom
English

 Programming Languages

Python
R
Java
JavaScript
PHP
SQL

 Web Development

HTML5
CSS3
Bootstrap
hugo
Hugo
django
Django
dotnet
.NET

 Software Engineering

Requirements
Design
Develop
Test
Methodologies
Source Control

 Machine Learning

Classification
Regression
Neural Networks
jupyter
Jupyter Notebook
scikit-learn
Scikit-Learn
tensorflow
Tensorflow

 Tools

Git
GitHub
xamarin
Xamarin
eclipse
Eclipse
visual-studio-code
Visual Studio Code
visual-studio
Visual Studio
HiTZ at VarDial 2025 NorSID: Overcoming Data Scarcity with Language Transfer and Automatic Data Annotation
HiTZ at VarDial 2025 NorSID: Overcoming Data Scarcity with Language Transfer and Automatic Data Annotation

In this paper we present our submission for the NorSID Shared Task as part of the 2025 VarDial Workshop (Scherrer et al., 2025), consisting of three tasks: Intent Detection, Slot Filling and Dialect Identification, evaluated using data in different dialects of the Norwegian language. For Intent Detection and Slot Filling, we have fine-tuned a multitask model in a cross-lingual setting, to leverage the xSID dataset available in 17 languages. In the case of Dialect Identification, our final submission consists of a model fine-tuned on the provided development set, which has obtained the highest scores within our experiments. Our final results on the test set show that our models do not drop in performance compared to the development set, likely due to the domain-specificity of the dataset and the similar distribution of both subsets. Finally, we also report an in-depth analysis of the provided datasets and their artifacts, as well as other sets of experiments that have been carried out but did not yield the best results. Additionally, we present an analysis on the reasons why some methods have been more successful than others; mainly the impact of the combination of languages and domain-specificity of the training data on the results.

Latxa Euskarazko Hizkuntza-Eredua
Latxa Euskarazko Hizkuntza-Eredua

Artikulu honetan Latxa hizkuntza-ereduak (HE) aurkeztuko ditugu, egun euskararako garatu diren HE handienak. Latxa HEek 7.000 miloi parametrotik 70.000 milioira bitartean dituzte, eta ingeleseko LLama 2 ereduetatik eratorriak dira. Horretarako, LLama 2 gainean aurreikasketa jarraitua izeneko prozesua gauzatu da, 4.3 milioi dokumentu eta 4.200 milioi token duen euskarazko corpusa erabiliz. Euskararentzat kalitate handiko ebaluazio multzoen urritasunari aurre egiteko, lau ebaluazio multzo berri bildu ditugu: EusProficiency, EGA azterketaren atariko frogako 5.169 galdera biltzen dituena; EusReading, irakurketaren ulermeneko 352 galdera biltzen dituena; EusTrivia, 5 arlotako ezagutza orokorreko 1.715 galdera biltzen dituena; eta EusExams, oposizioetako 16.774 galdera biltzen dituena. Datu-multzo berri hauek erabiliz, Latxa eta beste euskarazko HEak ebaluatu ditugu (elebakar zein eleanitzak), eta esperimentuek erakusten dute Latxak aurreko eredu ireki guztiak gainditzen dituela. Halaber, GPT-4 Turbo HE komertzialarekiko emaitza konpetitiboak lortzen ditu Latxak, hizkuntza-ezagutzan eta ulermenean, testu-irakurmenean zein ezagutza intentsiboa eskatzen duten atazetan atzeratuta egon arren. Bai Latxa ereduen familia, baita gure corpus eta ebaluazio-datu berriak ere lizentzia irekien pean daude publiko https://github. com/hitz-zentroa/latxa helbidean.

BertaQA: How Much Do Language Models Know About Local Culture?
BertaQA: How Much Do Language Models Know About Local Culture?

Large Language Models (LLMs) exhibit extensive knowledge about the world, but most evaluations have been limited to global or anglocentric subjects. This raises the question of how well these models perform on topics relevant to other cultures, whose presence on the web is not that prominent. To address this gap, we introduce BertaQA, a multiple-choice trivia dataset that is parallel in English and Basque. The dataset consists of a local subset with questions pertinent to the Basque culture, and a global subset with questions of broader interest. We find that state-of-the-art LLMs struggle with local cultural knowledge, even as they excel on global topics. However, we show that continued pre-training in Basque significantly improves the models’ performance on Basque culture, even when queried in English. To our knowledge, this is the first solid evidence of knowledge transfer from a low-resource to a high-resource language. Our analysis sheds light on the complex interplay between language and knowledge, and reveals that some prior findings do not fully hold when reassessed on local topics. Our dataset and evaluation code are available under open licenses at https://github.com/juletx/BertaQA.

Lessons from the Trenches on Reproducible Evaluation of Language Models
Lessons from the Trenches on Reproducible Evaluation of Language Models

Effective evaluation of language models remains an open challenge in NLP. Researchers and engineers face methodological issues such as the sensitivity of models to evaluation setup, difficulty of proper comparisons across methods, and the lack of reproducibility and transparency. In this paper we draw on three years of experience in evaluating large language models to provide guidance and lessons for researchers. First, we provide an overview of common challenges faced in language model evaluation. Second, we delineate best practices for addressing or lessening the impact of these challenges on research. Third, we present the Language Model Evaluation Harness (lm-eval): an open source library for independent, reproducible, and extensible evaluation of language models that seeks to address these issues. We describe the features of the library as well as case studies in which the library has been used to alleviate these methodological concerns.

Projects

*
Mejorando la seguridad de mi web

Mejorando la seguridad de mi web

Analizaré mi web con herramientas como Hardenize y Security Headers para detectar los aspectos de seguridad que se pueden mejorar.

Spiking Neural Network

Spiking Neural Network

Simulating the Izhikevich spiking neuron model using the Brian2 software

Image Caption Generation

Image Caption Generation

Automatic Image Caption Generation model that uses a CNN to condition a LSTM based language model.

Shape Classification

Shape Classification

The goal of the project is to compare different classification algorithms on the solution of plane and car shape datasets.

100Iragarki

100Iragarki

Your digital showcase Network Services and Applications 2019-2020

Academic Website

Academic Website

Academic personal website that includes a short description, social links, biography, interests, education, skills, experience, accomplishments, projects and contact info.

Antxieta Arkeologi Taldea Website

Antxieta Arkeologi Taldea Website

Antxieta Arkeologi Taldea website, a non-profit cultural group that develops archaeological research in Gipuzkoa.

BattleshipFeatureIDE

BattleshipFeatureIDE

Java Battleship FeatureIDE Software Product Line.

Community Detection

Community Detection

NIPS kongresuko autoreen komunitateak detektatzen metaheuristikoak erabiliz.

Comparing Writing Systems

Comparing Writing Systems

Comparing Writing Systems with Multilingual Grapheme-to-Phoneme and Phoneme-to-Grapheme Conversion.

Computational Syntax

Computational Syntax

Computational Syntax slides and exercises.

Corpus Linguistics

Corpus Linguistics

Corpus Linguistics slides, labs, assignments and data.

Deep Learning for Natural Language Processing

Deep Learning for Natural Language Processing

Deep Learning for Natural Language Processing slides, labs and assignments.

Dialbot

Dialbot

Ikasketa sakonean oinarritutako muturretik muturrerako solasaldi sistema.

Egunean Behin Visual Question Answering Dataset

Egunean Behin Visual Question Answering Dataset

This is a Visual Question Answering dataset based on questions from the game Egunean Behin. Egunean Behin is a popular Basque quiz game. The game consists on answering 10 daily multiple choice questions.

GitHub Website

GitHub Website

GitHub personal website that includes a photo, short description, social links and GitHub repositories and topics.

Grounding Language Models for Spatial Reasoning

Grounding Language Models for Spatial Reasoning

Grounding Language Models for Spatial Reasoning

HackerRank Challenge Solutions

HackerRank Challenge Solutions

Solutions for programming challenges in multiple languages.

Hyperpartisan News Analysis With Scattertext

Hyperpartisan News Analysis With Scattertext

Hyperpartisan News Analysis With Scattertext

Machine Learning and Neural Networks labs

Machine Learning and Neural Networks labs

Machine Learning and Neural Networks labs.

Machine Learning and Neural Networks lectures

Machine Learning and Neural Networks lectures

Machine Learning and Neural Networks lectures.

Machine Learning exercises with R

Machine Learning exercises with R

Machine Learning exercises with R.

MFDS

MFDS

Métodos Formales de Desarrollo de Software.

NLP Applications I - Text Classification, Sequence Labelling, Opinion Mining and Question Answering

NLP Applications I - Text Classification, Sequence Labelling, Opinion Mining and Question Answering

NLP Applications I - Text Classification, Sequence Labelling, Opinion Mining and Question Answering slides, labs and project.

NLP Applications II - Information Extraction, Question Answering, Recommender Systems and Conversational Systems

NLP Applications II - Information Extraction, Question Answering, Recommender Systems and Conversational Systems

NLP Applications II - Information Extraction, Question Answering, Recommender Systems and Conversational Systems slides, labs and project.

ProMeta

ProMeta

Metaereduetan oinarritutako softwarearen garapenerako prozesuen definizio eta ezarpenerako sistema.

ProMeta IO-System

ProMeta IO-System

ProMeta proiektua IO-System.

ProMeta ModelEditor

ProMeta ModelEditor

ProMeta proiektua ModelEditor.

Quiz

Quiz

Question game Web Systems 2019-2020

Twitter Sentiment and Emotion Analysis

Twitter Sentiment and Emotion Analysis

Twitter Sentiment and Emotion Analysis.

Zero-shot and Translation Experiments on XQuAD, MLQA and TyDiQA

Zero-shot and Translation Experiments on XQuAD, MLQA and TyDiQA

Zero-shot and Translation Experiments on XQuAD, MLQA and TyDiQA

 Contact