Álvaro Huertas García

Ph.D. Student

Short bio

Álvaro Huertas Garcia did his undergraduate studies in Biotechnology at Universidad de Salamanca. He then did his MSc in Bioinformatics and Computational Biology at Universidad Autónoma de Madrid. His MSc research project focused on developing an automatic system to counter COVID-19 misinformation and infodemic through semantic similarity. Currently is working on his Ph.D. thesis in Technology and Computational Science for Smart Cities at Universidad Politécnica de Madrid. He is an active member and collaborator in the non-profit organization SpainAI.

Areas of research

Social Network Analysis
Disinformation
Natural Language Processing

Projects as member

Caracterización inteligente de la veracidad de información asociada a la COVID-19 (CIVIC)

Scope: Industrial

Start date: October 10, 2020

End date: October 10, 2022
Iberian Digital Media Research and Fact-Checking Hub (IBERIFIER)

Scope: International

Start date: September 1, 2021

End date: February 29, 2024
DisTrack: Tracking disinformation in Online Social Networks through Deep Natural Language Processing (DisTrack)

Scope: Industrial

Start date: November 1, 2021

End date: December 31, 2022

Awards

Finalist of Innovation Talent Attraction Awards 2021 Community of Madrid (2021)

Description:

The Madrid City Council presents, at La Nave, the awards for the best doctoral theses and master’s theses presented in the last year at Madrid’s universities, in the field of innovation. For the selection of winners, a jury of researchers and university doctors of recognized prestige, and with the support of the CSIC.

Journal articles

2022

Martín, Alejandro; Huertas-Tato, Javier; Huertas-García, Álvaro; Villar-Rodríguez, Guillermo; Camacho, David

FacTeR-Check: Semi-automated fact-checking through Semantic Similarity and Natural Language Inference Journal Article

In: arXiv:2110.14532 [cs], 2022, (arXiv: 2110.14532).

Abstract | Links | BibTeX

@article{martin_facter-check_2022,

title = {FacTeR-Check: Semi-automated fact-checking through Semantic Similarity and Natural Language Inference},

author = {Alejandro Martín and Javier Huertas-Tato and Álvaro Huertas-García and Guillermo Villar-Rodríguez and David Camacho},

url = {http://arxiv.org/abs/2110.14532},

year  = {2022},

date = {2022-02-01},

urldate = {2022-02-01},

journal = {arXiv:2110.14532 [cs]},

abstract = {Our society produces and shares overwhelming amounts of information through Online Social Networks (OSNs). Within this environment, misinformation and disinformation have proliferated, becoming a public safety concern in most countries. Allowing the public and professionals to efficiently find reliable evidences about the factual veracity of a claim is a crucial step to mitigate this harmful spread. To this end, we propose FacTeR-Check, a multilingual architecture for semi-automated fact-checking that can be used for either applications designed for the general public and by fact-checking organisations. FacTeR-Check enables retrieving fact-checked information, unchecked claims verification and tracking dangerous information over social media. This architectures involves several modules developed to evaluate semantic similarity, to calculate natural language inference and to retrieve information from Online Social Networks. The union of all these components builds a semi-automated fact-checking tool able of verifying new claims, to extract related evidence, and to track the evolution of a hoax on a OSN. While individual modules are validated on related benchmarks (mainly MSTS and SICK), the complete architecture is validated using a new dataset called NLI19-SP that is publicly released with COVID-19 related hoaxes and tweets from Spanish social media. Our results show state-of-the-art performance on the individual benchmarks, as well as producing a useful analysis of the evolution over time of 61 different hoaxes.},

note = {arXiv: 2110.14532},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

Publications in conferences

2021

Huertas-García, Álvaro; Huertas-Tato, Javier; Martín, Alejandro; Camacho, David

CIVIC-UPM at CheckThat! 2021: Integration of Transformers in Misinformation Detection and Topic Classification Proceedings Article

In: Conference and Labs of the Evaluation Forum (CLEF) Working Notes, pp. 520–530, 2021.

Abstract | Links | BibTeX

Huertas-García, Álvaro; Huertas-Tato, Javier; Martín, Alejandro; Camacho, David

Countering Misinformation Through Semantic-Aware Multilingual Models Proceedings Article

In: Yin, Hujun; Camacho, David; Tino, Peter; Allmendinger, Richard; Tallón-Ballesteros, Antonio J.; Tang, Ke; Cho, Sung-Bae; Novais, Paulo; Nascimento, Susana (Ed.): Intelligent Data Engineering and Automated Learning – IDEAL 2021, pp. 312–323, Springer International Publishing, Cham, 2021, ISBN: 978-3-030-91608-4.

Abstract | Links | BibTeX

@inproceedings{huertas-garcia_countering_2021,

title = {Countering Misinformation Through Semantic-Aware Multilingual Models},

author = {Álvaro Huertas-García and Javier Huertas-Tato and Alejandro Martín and David Camacho},

editor = {Hujun Yin and David Camacho and Peter Tino and Richard Allmendinger and Antonio J. Tallón-Ballesteros and Ke Tang and Sung-Bae Cho and Paulo Novais and Susana Nascimento},

doi = {10.1007/978-3-030-91608-4_31},

isbn = {978-3-030-91608-4},

year  = {2021},

date = {2021-01-01},

urldate = {2021-01-01},

booktitle = {Intelligent Data Engineering and Automated Learning – IDEAL 2021},

pages = {312--323},

publisher = {Springer International Publishing},

address = {Cham},

abstract = {The presence of misinformation and harmful content on social networks is an emerging problem that endangers public health. One of the most successful approaches for detecting, assessing, and providing prompt responses to this misinformation problem is Natural Language Processing (NLP) techniques based on semantic similarity. However, language constitutes one of the most significant barriers to address, denoting the need to develop multilingual tools for an effective fight against misinformation. This paper presents an approach for countering misinformation through a semantic-aware multilingual architecture. Due to the specificity of the task addressed, which involves assessing the level of similarity between a pair of texts in a multilingual scenario, we built an extension of the well-known Semantic Textual Similarity Benchmark (STSb) to 15 languages. This new dataset allows to fine-tune and evaluate multilingual models based on Transformers with a siamese network topology on monolingual and cross-lingual Semantic Textual Similarity (STS) tasks, achieving a maximum average Spearman correlation coefficient of 83.60%. We validate our proposal using the Covid-19 MLIA @ Eval Multilingual Semantic Search Task. The results reported demonstrate that semantic-aware multilingual architectures are successful at measuring the degree of similarity between pairs of texts, while broadening our understanding of the multilingual capabilities of this type of models. The results and the new multilingual STS Benchmark data presented and made publicly in this study constitute an initial step towards extending methods proposed in the literature that employ semantic similarity to combat misinformation at a multilingual level.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

Other publications

2022

Huertas-García, Álvaro; Martín, Alejandro; Huertas-Tato, Javier; Camacho, David

Exploring Dimensionality Reduction Techniques in Multilingual Transformers Miscellaneous

CoRR, 2022.

Abstract | Links | BibTeX

@misc{nokey,

title = {Exploring Dimensionality Reduction Techniques in Multilingual Transformers},

author = {Álvaro Huertas-García and Alejandro Martín and Javier Huertas-Tato and David Camacho},

url = {https://doi.org/10.48550/arxiv.2204.08415},

doi = {10.48550/ARXIV.2204.08415},

year  = {2022},

date = {2022-04-18},

urldate = {2022-04-18},

abstract = {Both in scientific literature and in industry,, Semantic and context-aware Natural Language Processing-based solutions have been gaining importance in recent years. The possibilities and performance shown by these models when dealing with complex Language Understanding tasks is unquestionable, from conversational agents to the fight against disinformation in social networks. In addition, considerable attention is also being paid to developing multilingual models to tackle the language bottleneck. The growing need to provide more complex models implementing all these features has been accompanied by an increase in their size, without being conservative in the number of dimensions required. This paper aims to give a comprehensive account of the impact of a wide variety of dimensional reduction techniques on the performance of different state-of-the-art multilingual Siamese Transformers, including unsupervised dimensional reduction techniques such as linear and nonlinear feature extraction, feature selection, and manifold techniques. In order to evaluate the effects of these techniques, we considered the multilingual extended version of Semantic Textual Similarity Benchmark (mSTSb) and two different baseline approaches, one using the pre-trained version of several models and another using their fine-tuned STS version. The results evidence that it is possible to achieve an average reduction in the number of dimensions of 91.58%±2.59% and 54.65%±32.20%, respectively. This work has also considered the consequences of dimensionality reduction for visualization purposes. The results of this study will significantly contribute to the understanding of how different tuning approaches affect performance on semantic-aware tasks and how dimensional reduction techniques deal with the high-dimensional embeddings computed for the STS task and their potential for highly demanding NLP tasks },

howpublished = {CoRR},

keywords = {},

pubstate = {published},

tppubtype = {misc}

}

2021

Huertas-García, Álvaro

Automatic information search for countering covid-19 misinformation through semantic similarity Masters Thesis

Universidad Autónoma de Madrid, 2021.

Abstract | Links | BibTeX

@mastersthesis{huertas-garcia_uam_2021,

title = {Automatic information search for countering covid-19 misinformation through semantic similarity},

author = {Álvaro Huertas-García},

url = {https://repositorio.uam.es/handle/10486/695067},

year = {2021},

date = {2021-02-26},

urldate = {2021-02-26},

school = {Universidad Autónoma de Madrid},

abstract = {Information quality in social media is an increasingly important issue and misinformation problem has become even more critical in the current COVID-19 pandemic, leading people exposed to false and potentially harmful claims and rumours. Civil society organizations, such as the World Health Organization, have demanded a global call for action to promote access to health information and mitigate harm from health misinformation. Consequently, this project pursues countering the spread of COVID-19 infodemic and its potential health hazards. In this work, we give an overall view of models and methods that have been employed in the NLP field from its foundations to the latest state-of-the-art approaches. Focusing on deep learning methods, we propose applying multilingual Transformer models based on siamese networks, also called bi-encoders, combined with ensemble and PCA dimensionality reduction techniques. The goal is to counter COVID-19 misinformation by analyzing the semantic similarity between a claim and tweets from a collection gathered from official fact-checkers verified by the International Fact-Checking Network of the Poynter Institute. It is factual that the number of Internet users increases every year and the language spoken determines access to information online. For this reason, we give a special effort in the application of multilingual models to tackle misinformation across the globe. Regarding semantic similarity, we firstly evaluate these multilingual ensemble models and improve the result in the STS-Benchmark compared to monolingual and single models. Secondly, we enhance the interpretability of the models’ performance through the SentEval toolkit. Lastly, we compare these models’ performance against biomedical models in TREC-COVID task round 1 using the BM25 Okapi ranking method as the baseline. Moreover, we are interested in understanding the ins and outs of misinformation. For that purpose, we extend interpretability using machine learning and deep learning approaches for sentiment analysis and topic modelling. Finally, we developed a dashboard to ease visualization of the results. In our view, the results obtained in this project constitute an excellent initial step toward incorporating multilingualism and will assist researchers and people in countering COVID-19 misinformation.},

keywords = {},

pubstate = {published},

tppubtype = {mastersthesis}

}

Information quality in social media is an increasingly important issue and misinformation problem has become even more critical in the current COVID-19 pandemic, leading people exposed to false and potentially harmful claims and rumours. Civil society organizations, such as the World Health Organization, have demanded a global call for action to promote access to health information and mitigate harm from health misinformation. Consequently, this project pursues countering the spread of COVID-19 infodemic and its potential health hazards. In this work, we give an overall view of models and methods that have been employed in the NLP field from its foundations to the latest state-of-the-art approaches. Focusing on deep learning methods, we propose applying multilingual Transformer models based on siamese networks, also called bi-encoders, combined with ensemble and PCA dimensionality reduction techniques. The goal is to counter COVID-19 misinformation by analyzing the semantic similarity between a claim and tweets from a collection gathered from official fact-checkers verified by the International Fact-Checking Network of the Poynter Institute. It is factual that the number of Internet users increases every year and the language spoken determines access to information online. For this reason, we give a special effort in the application of multilingual models to tackle misinformation across the globe. Regarding semantic similarity, we firstly evaluate these multilingual ensemble models and improve the result in the STS-Benchmark compared to monolingual and single models. Secondly, we enhance the interpretability of the models’ performance through the SentEval toolkit. Lastly, we compare these models’ performance against biomedical models in TREC-COVID task round 1 using the BM25 Okapi ranking method as the baseline. Moreover, we are interested in understanding the ins and outs of misinformation. For that purpose, we extend interpretability using machine learning and deep learning approaches for sentiment analysis and topic modelling. Finally, we developed a dashboard to ease visualization of the results. In our view, the results obtained in this project constitute an excellent initial step toward incorporating multilingualism and will assist researchers and people in countering COVID-19 misinformation.

Talks and seminars

I.E.S Sierra Calera

Type: Invited Talk

Date: June 20, 2022

Location: Santa Marta de los Barros, Badajoz

Description:

Introduction to Aritficial Intelligence for young students (14-18 years old) in a two hours session.
Regarding our dissemination and open-science objectives, we have collaborated with High Schools (“Institutos de Educación Secundaria”) giving talks about Aritificial Intelligence and new job trends in the Technology sector.

Álvaro Huertas García

Ph.D. Student

Caracterización inteligente de la veracidad de información asociada a la COVID-19 (CIVIC)

Iberian Digital Media Research and Fact-Checking Hub (IBERIFIER)

DisTrack: Tracking disinformation in Online Social Networks through Deep Natural Language Processing (DisTrack)

Finalist of Innovation Talent Attraction Awards 2021 Community of Madrid (2021)

2022

2021

2022

2021

I.E.S Sierra Calera