83 citations · 119 across the 10 of their papers we have counts for
11 papers
Do Neural Retrievers Prefer Certain Documents? Evidence of Learned Relevance Priors
Francisco Valentini, Edgar Altszyler, Martin Fajcik
Neural retrievers are trained to estimate query-document relevance from annotated query-document pairs. Yet annotation protocols may not purely reflect relevance: they select only…
MessIRve: A Large-Scale Spanish Information Retrieval Dataset
Francisco Valentini, Viviana Cotik, Damián Furman +3
Information retrieval (IR) is the task of finding relevant documents in response to a user query. Although Spanish is the second most spoken native language, there are few Spanish…
Mining Reasons For And Against Vaccination From Unstructured Data Using Nichesourcing and AI Data Augmentation
Damián Ariel Furman, Juan Junqueras, Z. Burçe Gümüslü +4
We present Reasons For and Against Vaccination (RFAV), a dataset for predicting reasons for and against vaccination, and scientific authorities used to justify them, annotated thro…
The Undesirable Dependence on Frequency of Gender Bias Metrics Based on Word Embeddings
Francisco Valentini, Germán Rosati, Diego Fernandez Slezak +1
Numerous works use word embedding-based metrics to quantify societal biases and stereotypes in texts. Recent studies have found that word embeddings can capture semantic similarity…
Investigating the Frequency Distortion of Word Embeddings and Its Impact on Bias Metrics
Francisco Valentini, Juan Cruz Sosa, Diego Fernandez Slezak +1
Recent research has shown that static word embeddings can encode word frequency information. However, little has been studied about this phenomenon and its effects on downstream ta…
On the Interpretability and Significance of Bias Metrics in Texts: a PMI-based Approach
Francisco Valentini, Germán Rosati, Damián Blasi +2
In recent years, word embeddings have been widely used to measure biases in texts. Even if they have proven to be effective in detecting a wide variety of biases, metrics based on…
Gender bias in magazines oriented to men and women: a computational approach
Diego Kozlowski, Gabriela Lozano, Carla M. Felcher +2
Cultural products are a source to acquire individual values and behaviours. Therefore, the differences in the content of the magazines aimed specifically at women or men are a mean…
Zero-shot Multi-Domain Dialog State Tracking Using Descriptive Rules
Edgar Altszyler, Pablo Brusco, Nikoletta Basiou +2
In this work, we present a framework for incorporating descriptive logical rules in state-of-the-art neural networks, enabling them to learn how to handle unseen labels without the…
Corpus specificity in LSA and Word2vec: the role of out-of-domain documents
Edgar Altszyler, Mariano Sigman, Diego Fernandez Slezak
Latent Semantic Analysis (LSA) and Word2vec are some of the most widely used word embeddings. Despite the popularity of these techniques, the precise mechanisms by which they acqui…
Comparative study of LSA vs Word2vec embeddings in small corpora: a case study in dreams database
Edgar Altszyler, Mariano Sigman, Sidarta Ribeiro +1
Word embeddings have been extensively studied in large text datasets. However, only a few studies analyze semantic representations of small corpora, particularly relevant in single…
Ultrasensitivity on signaling cascades revisited: Linking local and global ultrasensitivity estimations
Edgar Altszyler, Alejandra Ventura, Alejandro Colman-Lerner +1
Ultrasensitive response motifs, which are capable of converting graded stimulus in binary responses, are very well-conserved in signal transduction networks. Although it has been s…