Zobrazeno 1 - 10
of 154
pro vyhledávání: '"Mendoza, Marcelo"'
While civilized users employ social media to stay informed and discuss daily occurrences, haters perceive these platforms as fertile ground for attacking groups and individuals. The prevailing approach to counter this phenomenon involves detecting su
Externí odkaz:
http://arxiv.org/abs/2405.13011
Autor:
Mendoza, Marcelo, Valenzuela, Sebastián, Núñez-Mussa, Enrique, Padilla, Fabián, Providel, Eliana, Campos, Sebastián, Bassi, Renato, Riquelme, Andrea, Aldana, Valeria, López, Claudia
Publikováno v:
Applied Sciences 2023, 13(9), 5347
Information disorders on social media can have a significant impact on citizens' participation in democratic processes. To better understand the spread of false and inaccurate information online, this research analyzed data from Twitter, Facebook, an
Externí odkaz:
http://arxiv.org/abs/2306.14378
Autor:
Mendoza, Marcelo, Bro, Naim
Publikováno v:
PLoS ONE 16(9): e0256603 (2021)
From administrative registers of last names in Santiago, Chile, we create a surname affinity network that encodes socioeconomic data. This network is a multi-relational graph with nodes representing surnames and edges representing the prevalence of i
Externí odkaz:
http://arxiv.org/abs/2306.01218
Autor:
Bro, Naim, Mendoza, Marcelo
Publikováno v:
PLoS ONE 16(1): e0244372 (2021)
Based on a geocoded registry of more than four million residents of Santiago, Chile, we build two surname-based networks that reveal the city's population structure. The first network is formed from paternal and maternal surname pairs. The second net
Externí odkaz:
http://arxiv.org/abs/2306.01197
Autor:
Araujo, Vladimir, Carvallo, Andrés, Kundu, Souvik, Cañete, José, Mendoza, Marcelo, Mercer, Robert E., Bravo-Marquez, Felipe, Moens, Marie-Francine, Soto, Alvaro
Due to the success of pre-trained language models, versions of languages other than English have been released in recent years. This fact implies the need for resources to evaluate these models. In the case of Spanish, there are few ways to systemati
Externí odkaz:
http://arxiv.org/abs/2204.07571
Current language models are usually trained using a self-supervised scheme, where the main focus is learning representations at the word or sentence level. However, there has been limited progress in generating useful discourse-level representations.
Externí odkaz:
http://arxiv.org/abs/2109.04602
Summarization has usually relied on gold standard summaries to train extractive or abstractive models. Social media brings a hurdle to summarization techniques since it requires addressing a multi-document multi-author approach. We address this chall
Externí odkaz:
http://arxiv.org/abs/2106.03953
The field of natural language understanding has experienced exponential progress in the last few years, with impressive results in several tasks. This success has motivated researchers to study the underlying knowledge encoded by these models. Despit
Externí odkaz:
http://arxiv.org/abs/2105.13471
Autor:
Silva, Alfredo, Mendoza, Marcelo
Publikováno v:
8th International Conference on Artificial Intelligence and Applications (AIAP 2021), January 23 ~ 24, 2021, Zurich, Switzerland
Word embeddings are vital descriptors of words in unigram representations of documents for many tasks in natural language processing and information retrieval. The representation of queries has been one of the most critical challenges in this area be
Externí odkaz:
http://arxiv.org/abs/2105.12788