no code implementations • EMNLP 2020 • Jose Manuel Gomez-Perez, Ra{\'u}l Ortega
Textbook Question Answering is a complex task in the intersection of Machine Comprehension and Visual Question Answering that requires reasoning with multimodal information from text and diagrams.
1 code implementation • 13 Apr 2021 • Andres Garcia-Silva, Cristian Berrio, Jose Manuel Gomez-Perez
In this paper we shed light on the impact of fine-tuning over social media data in the internal representations of neural language models.
no code implementations • 13 Apr 2021 • Andres Garcia-Silva, Ronald Denaux, Jose Manuel Gomez-Perez
In essence, embedding algorithms work by optimizing the distance between a word and its usual context in order to generate an embedding space that encodes the distributional representation of words.
no code implementations • EACL 2021 • Georg Rehm, Stelios Piperidis, Kalina Bontcheva, Jan Hajic, Victoria Arranz, Andrejs Vasi{\c{l}}jevs, Gerhard Backfried, Jose Manuel Gomez-Perez, Ulrich Germann, R{\'e}mi Calizzano, Nils Feldhus, Stefanie Hegele, Florian Kintzel, Katrin Marheinecke, Julian Moreno-Schneider, Dimitris Galanis, Penny Labropoulou, Miltos Deligiannis, Katerina Gkirtzou, Athanasia Kolovou, Dimitris Gkoumas, Leon Voukoutis, Ian Roberts, Jana Hamrlova, Dusan Varis, Lukas Kacena, Khalid Choukri, Val{\'e}rie Mapelli, Micka{\"e}l Rigault, Julija Melnika, Miro Janosik, Katja Prinz, Andres Garcia-Silva, Cristian Berrio, Ondrej Klejch, Steve Renals
Europe is a multilingual society, in which dozens of languages are spoken.
1 code implementation • 20 Jan 2021 • Andres Garcia-Silva, Jose Manuel Gomez-Perez
We compare and evaluate the subset of the most attended words with feature selection methods normally used for text classification in order to characterize self-attention as a possible feature selection approach.
no code implementations • 1 Oct 2020 • Jose Manuel Gomez-Perez, Raul Ortega
Textbook Question Answering is a complex task in the intersection of Machine Comprehension and Visual Question Answering that requires reasoning with multimodal information from text and diagrams.
1 code implementation • 28 Aug 2020 • Ronald Denaux, Jose Manuel Gomez-Perez
In this paper we propose an architecture based on a core concept of Credibility Reviews (CRs) that can be used to build networks of distributed bots that collaborate for misinformation detection.
1 code implementation • 24 Sep 2019 • Ronald Denaux, Jose Manuel Gomez-Perez
Deep learning currently dominates the benchmarks for various NLP tasks and, at the basis of such systems, words are frequently represented as embeddings --vectors in a low dimensional space-- learned from large text corpora and various algorithms have been proposed to learn both word and concept embeddings.
1 code implementation • 19 Sep 2019 • Jose Manuel Gomez-Perez, Raul Ortega
Compared to natural images, understanding scientific figures is particularly hard for machines.
no code implementations • 27 Sep 2018 • Andres Garcia-Silva, Jose Manuel Gomez-Perez, Raul Palma, Marcin Krystek, Simone Mantovani, Federica Foglini, Valentina Grande, Francesco De Leo, Stefano Salvi, Elisa Trasati, Vito Romaniello, Mirko Albani, Cristiano Silvagni, Rosemarie Leone, Fulvio Marelli, Sergio Albani, Michele Lazzarini, Hazel J. Napier, Helen M. Glaves, Timothy Aldridge, Charles Meertens, Fran Boler, Henry W. Loescher, Christine Laney, Melissa A Genazzio, Daniel Crawl, Ilkay Altintas
Data-intensive science communities are progressively adopting FAIR practices that enhance the visibility of scientific breakthroughs and enable reuse.
no code implementations • 5 Apr 2018 • Andres Garcia, Jose Manuel Gomez-Perez
The emergence of knowledge graphs in the scholarly communication domain and recent advances in artificial intelligence and natural language processing bring us closer to a scenario where intelligent systems can assist scientists over a range of knowledge-intensive tasks.