Blog
Check out my latest news here!
My participation in the FDP Program as Chief Guest!
October 2020
I participated in the Five-day Faculty Development Programme (FDP) on Artificial Intelligence in Natural Language Processing organized virtually by The School of Computer Applications, KIIT University. Check some of the news here, here, and here!
Idiap and UAM, winners of the fake-news detection task at MEX-A3T
June 2020
During the 2020 edition of the MEX-A3T, our team, Idiap & UAM, obtained the best performance on the detection of fake-news. Check out the description paper here! Also mentioned on Twitter!
My sabbatical at Idiap!
August 2019
I'll be working for one year at Idiap as part of my sabbatical leave. Check out the full story here!!
HWxPI track: Handwritten texts for Personality Identification challenge at ICPR-2018
August 2018
Special issue on Looking At People: Analyzing Human Behavior from Social Media Data, International Journal of Computer Vision. Consider submitting a paper here!.
Congratulations to Ángel Callejas for its participation in the VII CoLiCo and V SeLiFo at the UNAM
August 2015
During the VII CoLiCo and V SeLiFo Ángel talked about its bachelor thesis, particularly about the proposed method for automatically infer conversational rules for online dialog systems. If you are interested on this work, see the full thesis document here.
Cross-Language Detection of Source Code Re-use Track
May 2015
Call for participation for 2015 SOCO edition now open. This year we introduce the cross-language challenge. (http://users.dsic.upv.es/grupos/nle/clsoco/)
Students from the LTSI from UAMC won at the first NLP Jakatón
April 2015
Congratulations!.
Aarón Ramírez y Ángel Callejas, ambos estudiantes de la Licenciatura en Tecnologías y Sistemas de Información de la UAM Cuajimalpa, resultan ganadores del primer jakatonpln analizando la polaridad sentimental de periódicos(http://golem.iimas.unam.mx/jakaton/)
LyR Team wons the first place for Source Code Re-use detection in Java Programming language
December 2014
Congratulations!.
Congratulations to Aarón Ramírez, Gabriela Ramírez and Christian Sánchez for their great work during SOCO 2014 competition. Check out the online article on Noticieros Televisa (http://noticieros.televisa.com/mexico-df/1503/alumno-uam-gana-concurso-detectar-plagios-india/)
PAN Track on Detection of SOurce COde Re-use (SOCO)
May 2014
Our very happy logo.
I'm a part of the team that organizes the first interational competition on Source Code Re-use Detection. Read the call for participation at http://www.dsic.upv.es/grupos/nle/soco
Estancias de Investigación en la UNSL, Argentina
April 2014
Giving a talk! :).
Durante mi estancia como Profesor Invitado en el Departamento de Informática de la Universidad Nacional de San Luis UNSL,Argentina, se dió una charla sobre las técnicas más recientes para la detección de Plagio en Código Fuente.
Ver más información en: http://webfmn.unsl.edu.ar/boletines/boletin457/noticia1.htm
Nota en el UNIVERSAL sobre nuestro trabajo de Identificación de Acosadores Sexuales en Internet
December 2013
Vista la nota publicada en el Universal relacionada al trabajo realizado en conjunto con el LabTL-INAOE sobre la Identificación de Depredadores Sexuales http://www.eluniversal.com.mx/nacion-mexico/2013/combaten-a-depredadores-de-menores-971033.html
Our work for Author Profiling won the 1st place during PAN@CLEF 2013
November 2013
A picture of the team.
El Laboratorio de Lingüística Forense de la Universidad Pompeu Fabra de Barcelona, España, otorgó un premio al equipo integrado por los doctores Manuel Montes, Luis Villaseñor y Hugo Escalante, investigadores del Instituto Nacional de Astrofísica, Óptica y Electrónica, y por Adrián Pastor López Monroy, estudiante de doctorado del Instituto Nacional de Astrofísica, Óptica y Electrónica (INAOE), por un proyecto de inteligencia artificial para determinar el perfil de los usuarios de una red social. (http://mexicocyt.org.mx/noticias_eventos/7698)
Best Paper Award at COMIA 2013
June 2013
Congrats to Gilberto!!.
Our work about Polarity Classification in tweets won the best paper award at COMIA 2013. Congratulations Gilberto! Really nice work… :)
New accepted paper about Sexual Predators Identification
April 2013
Our paper describes a novel approach for sexual predator detection in chat conversations based on sequences of classifiers. The proposed approach divides documents into three parts, which, we hypothesize, correspond to the different stages that a predator employs when approaching a child. Local classifiers are trained for each part of the documents and their outputs are combined by a chain strategy: predictions of a local classifier are used as extra inputs for the next local classifier. Additionally, we propose a ringbased strategy, in which the chaining process is iterated several times, with the goal of further improving the performance of our method. We report experimental results on the corpus used in the first international competition on sexual predator identification (PAN’12). Experimental results show that the proposed method outperforms a standard (global) classification technique for the different settings we consider; besides the proposed method compares favorably with most methods evaluated in the PAN’12 competition.
This paper is going to be presented at the 4th Workshop on Computational Approaches to Subjectivity, Sentiment & Social Media Analysis (WASSA 2013), which is held in conjuntion with the NAACL-HLT 2013 Conference
1st place during the first International Competition in Sexual Predators Identification
July 2012
A picture of the team!!.
Our system , jointly developed by the Language Technologies Lab. from INAOE and the Language and Reasoning Group from UAM for the Sexual Predators Identification task at the PAN 2012, won the 1st place among 16 participants. Our presented system focuses on the problem of identifying sexual predators in a set of suspicious chatting. It is mainly based on the following hypotheses: (i) terms used in the process of child exploitation are categorically and psychologically different than terms used in general chatting; and (ii) predators usually apply the same course of conduct pattern when they are approaching a child. Based on these hypotheses, our participation at the PAN 2012 aimed to demonstrate that it is possible to train a classifier to learn those particular terms that turn a chat conversa- tion into a case of online child exploitation; and, that it is also possible to learn the behavioural patters of predators during a chat conversation allowing us to accurately distinguish victims from predators.
You can find the official results in the PAN@CLEF 2012 web’s page.