Skip to content
View guerreropaula's full-sized avatar

Organizations

@pguerrero-igutierrez

Block or report guerreropaula

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
guerreropaula/README.md

Paula Guerrero

Personal website

Translator | NLP Engineer | Computational Linguist

Currently pursuing a Master’s degree in Natural Language Analysis and Processing (NLP) at UPV/EHU (San Sebastián). Passionate about language and technologies, with a specific interest in NLP applications within Machine Translation in low-resource settings.


Experience

  • NLP Intern at 1MillionBot | Alicante, Spain (2026)

    • Training and configuration of conversational AI models for customer service applications.
    • RAG conversational systems.
  • NLP Intern at Prompsit Language Engineering | Elche, Spain (2025)

    • Corpus validation and annotation for the MaCoCu project (EU-funded, underresourced languages)
    • MT system training
    • Identification and categorization of errors in multilingual corpora.
    • Quality assessment of web-crawled corpora

Education

  • MSc in Language Analysis and Processing (2025 – 2027) — University of the Basque Country (UPV/EHU)

    • Deep learning, machine translation, prompt engineering, corpus creation and curation, LLM fine-tuning and refinement, Name Entity Recognition, RAG, Reinforcement Learning, Text Summarization
  • BA in Translation and Interpreting (2021 – 2025) — University of Alicante

    • Erasmus exchange at Université Saint-Louis (Brussels, 2023–2024)

Skills

  • NLP & AI: PyTorch, scikit-learn, fine-tuning, NLTK, Spacy, CAT Tools
  • Programming: Python, Unix/Bash
  • Languages: Spanish & Valencian (native), English & French (C1/C2), Chinese (B1), German (A2)

Main projects

dialectal-es-va-RL · Feb 2026 – present

Fine-tuned TranslateGemma-4B using Supervised Fine-Tuning (SFT) and Reinforcement Learning (GRPO) to improve translation quality for the low-resource Valencian dialect.

paracrawl/keops · Feb 2025

MaCoCu Corpus Validation (Keops Platform) — ★ 15 · 🍴 5 Alignment and quality assurance of bilingual corpora. Guideline refinement.

Clinical Text Simplification with Fine-Tuned LLMs (Qwen & Llama)

Fine-tuned Qwen3.5-0.8B and Llama-3.2-1B with LoRA on the CLARA-MeD clinical corpus for automatic medical text simplification in Spanish.

Informal Language Machine Translation Shared Task RAG-based and few-shot approaches for machine translation of colloquial Instagram direct messages from Spanish into Basque.

Connect

Pinned Loading

  1. paracrawl/keops paracrawl/keops Public

    Tool for manual evaluation of parallel sentences.

    PHP 15 5

  2. informal-MT-shared-task/informal-MT informal-MT-shared-task/informal-MT Public

    Python 1

  3. pguerrero-igutierrez/clinical-simplification pguerrero-igutierrez/clinical-simplification Public

    Clinical text simplifiers by fine-tuning Qwen and Llama with CLARA-MeD.

    Jupyter Notebook 1

  4. synthetic-corpus-ca-es synthetic-corpus-ca-es Public

    This repository contains the code and methodology for creating, processing, and analyzing a synthetic parallel bilingual corpus (ca-es).

    Python

  5. pguerrero-igutierrez/MT-domain-adaptation pguerrero-igutierrez/MT-domain-adaptation Public

    Domain adaptation for Catalan–Basque MT via synthetic data and LoRA fine-tuning of Latxa-Qwen3-8B across general, literary, and clinical domains.

    Python 1