Biography
Hi! I am Jessica López Espejel, a deep learning researcher with a passion for Artificial Intelligence (AI) topics. My research interests encompass various aspects of Natural Language Processing (NLP), such as text and code generation, and automatic evaluation. Currently, I am particularly fascinated by everything related to Large Language Models (LLMs).
Interests
- Artificial Intelligence
- Large Language Models
- Code/Text Generation
- Automatic Evaluation
Education
PhD in Artificial Intelligence, 2021
Sorbonne Paris Nord University and CEA-LIST, France
M.Sc., Computer Science and Mathematics, 2017
Benemérita Universidad Autónoma de Puebla, Mexico
Engineering in Computer Science, 2015
Benemérita Universidad Autónoma de Puebla, Mexico
Experience
Deep Learning Researcher
Responsibilities include:
- Develop and apply techniques for automated code generation in Java and SQL
- Fine-tune models, models, optimize parameters, and engineer prompts for superior performance
- Implement deployment of models for efficient execution
- Generate production-ready optimized code
- Publish scientific papers to validate the proposed solutions
Postdoctoral Researcher
Responsibilities include:
- Identifying the existence of diasporas from web search results using reinforcement learning
- Write optimized and clear code using best practices and efficient algorithms.
Researcher Ph.D. Student
Responsibilities include:
- Propose state-of-the-art methods for generating summaries automatically
- Suggest cutting-edge techniques for automatically evaluating summaries
- Provide Python classes to Bachelor’s students at ENSTA Paris
Software Developer
Responsibilities include:
- Java developer specializing in web services (front-end/back-end)
- Implementing security algorithms for webpage protection
Projects
*
Recent Publications
Quickly discover relevant content by filtering publications.
(2023).
GPT-3.5, GPT-4, or BARD? Evaluating LLMs reasoning ability in zero-shot setting and performance boosting through prompts.
In Natural Language Processing Journal.
(2023).
A comprehensive review of State-of-The-Art methods for Java code generation from Natural Language Text.
In Natural Language Processing Journal.
(2023).
JaCoText: A Pretrained Model for Java Code-Text Generation.
In International Journal of Computer and Systems Engineering.
(2021).
GeSERA: General-domain Summary Evaluation by Relevance Analysis.
In Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021).