Search Results for author: Marcelo Mendoza

Found 8 papers, 2 papers with code

Predicting affinity ties in a surname network

no code implementations2 Jun 2023 Marcelo Mendoza, Naim Bro

From administrative registers of last names in Santiago, Chile, we create a surname affinity network that encodes socioeconomic data.

Knowledge Base Completion

Augmenting BERT-style Models with Predictive Coding to Improve Discourse-level Representations

no code implementations EMNLP 2021 Vladimir Araujo, Andrés Villa, Marcelo Mendoza, Marie-Francine Moens, Alvaro Soto

Current language models are usually trained using a self-supervised scheme, where the main focus is learning representations at the word or sentence level.

Relationship Detection Sentence

Neural Abstractive Unsupervised Summarization of Online News Discussions

1 code implementation7 Jun 2021 Ignacio Tampe Palma, Marcelo Mendoza, Evangelos Milios

Our novel approach provides a summary that represents the most relevant aspects of a news item that users comment on, incorporating the social context as a source of information to summarize texts in online social networks.

Abstractive Text Summarization Unsupervised Text Summarization

Inspecting the concept knowledge graph encoded by modern language models

no code implementations Findings (ACL) 2021 Carlos Aspillaga, Marcelo Mendoza, Alvaro Soto

The field of natural language understanding has experienced exponential progress in the last few years, with impressive results in several tasks.

Natural Language Understanding Word Embeddings

A data-driven strategy to combine word embeddings in information retrieval

no code implementations26 May 2021 Alfredo Silva, Marcelo Mendoza

We use Idf combinations of embeddings to represent queries, showing that these representations outperform the average word embeddings recently proposed in the literature.

Ad-Hoc Information Retrieval Descriptive +3

Tracking the progress of Language Models by extracting their underlying Knowledge Graphs

no code implementations1 Jan 2021 Carlos Aspillaga, Marcelo Mendoza, Alvaro Soto

The state of the art, previously dominated by pre-trained word embeddings, is now being pushed forward by large pre-trained contextual representation models.

Knowledge Graphs Word Embeddings

Says who? Automatic Text-Based Content Analysis of Television News

no code implementations18 Jul 2013 Carlos Castillo, Gianmarco De Francisci Morales, Marcelo Mendoza, Nasir Khan

We perform an automatic analysis of television news programs, based on the closed captions that accompany them.

Cannot find the paper you are looking for? You can Submit a new open access paper.