Francisco Valentini's Projects
On the Interpretability and Significance of Bias Metrics in Texts: a PMI-based Approach (Valentini et al., ACL 2023)
ColBERT: state-of-the-art neural search (SIGIR'20, TACL'21, NeurIPS'21, NAACL'22, CIKM'22)
Contriever: Unsupervised Dense Information Retrieval with Contrastive Learning
Answers to Stanford's CS224n 2019 assignments
Course taught at ECLAC Buenos Aires - October 2019
Network analysis of brain activity during sleep
Detection of Hyades stars (Master in Data Mining - UBA)
Network analysis of OECD Inter-Country Input-Output Tables
Imagen de candidatos con datos de Elypsis (Maestria DM - Aprendizaje Automatico - TP1)
Maestria DM - Data Mining - TP 2 - Reglas de asociacion de ataques de tiburones
Analysis of opinions in Twitter during the Bolivian crisis
Prediccion de genero de tweets (Maestria DM - Aprendizaje Automatico - TP 2)
Maestria DM - Data Mining - TP 1 - Popularidad de tweets
DSPy: The framework for programming with foundation models
The Undesirable Dependence on Frequency of Gender Bias Metrics Based on Word Embeddings (Valentini et al., Findings 2022)
Investigating the Frequency Distortion of Word Embeddings and Its Impact on Bias Metrics (Valentini et al., Findings EMNLP 2023)
Forward-Looking Active REtrieval-augmented generation (FLARE)
Contents used in the course "Anรกlisis Predictivo" (Licenciatura en Analรญtica Empresarial y Social, ITBA)
NLP with disaster tweets (Kaggle competition)
Anomaly detection and 7-day mortality prediction with MIMIC-III database
Miscellaneous code for me, myself and I
Notebooks about stuff
Stats, plots and data about the NBA
Pyserini is a Python toolkit for reproducible information retrieval research with sparse and dense representations.
Shiny app for seasonal adjustment with X-13ARIMA-SEATS
Estadรญsticas de transacciones de MonedaPAR