Helena Montserrat Gómez Adorno

Helena Montserrat Gómez Adorno

Associate Researcher C - SNI Level 1 and Artificial Intelligence professor

IIMAS,UNAM

About me…

I am faculty at Universidad Nacional Autónoma de México (UNAM) in the Instituto de Investigaciones en Matemáticas Aplicadas y Sistemas (IIMAS). My research areas are natural language processing, computational linguistics and information retrieval; specifically applications, search for answers, semantic similarity, attribution of authorship and author profiling. During my Ph.D. I introduced text representation structures based on graphs to facilitate NLP tasks and a new method to calculate the semantic similarity between texts, called soft cosine similarity, which considers the semantic information of characteristics such as words, n-grams, POS tags, etc.

Curriculum Vitae

Dr. Helena Gómez Adorno is a professor of Artificial Intelligence at IIMAS-UNAM. Among her research interests areas are natural language processing, computational linguistics, and information retrieval; specifically, question answering, semantic similarity, authorship attribution, and author profiling. Lead a research and development team to implement intelligent systems with the help of machine learning and neural networks.

Awards and honours

  • Lázaro Cárdenas 2019” Prize for remarkable performance as PhD. student in Engineering, Physical & Mathematical Sciences area from Instituto Politécnico Nacional.
  • Award for the best academic performance of doctoral students of the Instituto Politécnico Nacional (IPN) 2016. There are approximately 50 doctoral students at the IPN. The diploma is awards to the best scores and publications.
  • Scholarship “Award of Merit” for international students from the Ministry of Foreign Relations (SRE) of the Mexican Government for Master’s studies, 2011–2013. The SRE awards two scholarships per country by year.
  • Best Paper Award for the work entitled “Author Profiling with doc2vec Neural Network-Based Document Embeddings” of the 15th Mexico International Congress of Artificial Intelligence (MICAI) 2016.

Research stays

  • Instituto de Ingeniería - UNAM (Mexico), February - July 2018.
  • IBM Deutschland Research and Development GmbH (Germany), July - September 2017.

Interests

  • Artificial Intelligence
  • Natural Language Processing
  • Database
  • Machine Learning
  • Text Mining

Education

    PhD , Centro de Investigación en Computación (CIC), Instituto Politécnico Nacional (IPN), Mexico (2018)
    MSc , Facultad de Ciencias de la Computación, Benemérita Universidad Autónoma de Puebla (BUAP), México (2013)
    BS , Facultad Politénica, Universidad Nacional de Asunción, Paraguay (2005)

Service: COVID-19 in Twitter México · UNAM Posgraduate adviser · UNAM Social Service Program · NLP Summer School 2020 · MEX-A3T Workshop 2020 ·

Teaching

Inteligencia Artificial, 2020
Posgrado en Ciencia e Ingeniería de la Computación. UNAM
Minería de Textos, 2020
Posgrado en Ciencia e Ingeniería de la Computación.UNAM
Minería de Grafos, 2019
Posgrado en Ciencia e Ingeniería de la Computación. UNAM

Team

Students seeking mentoring in Natural Language Processing may contact me to discuss the possibility. I work closely with the Linguistic Ingeniering group.

Ph.D. Students
01/2019 -  
Ph.D. Student, Posgrado en Ciencia e Ingeniería de la Computación - UNAM
01/2020 -  
Ph.D. Student, Posgrado en Ciencia e Ingeniería de la Computación - UNAM
07/2020 -  
Ph.D. Student, Centro de Investigación en Computación - IPN
Master Students
07/2018 -  
Master Student, Posgrado en Ciencia e Ingeniería de la Computación - UNAM
07/2019 -  
Master Student, Posgrado en Ciencia e Ingeniería de la Computación - UNAM
07/2019 -  
Master Student, Posgrado en Ciencia e Ingeniería de la Computación - UNAM
Past Students
07/2018 - 01/2020 
Master Student, Posgrado en Ciencia e Ingeniería de la Computación
07/2018 - 07/2020 
Master Student, Centro de Investigación en Computación - IPN
Social Service Students
03/2020  
Social Service Student, Undergaduate Student. Facultad de Ciencias, UNAM
03/2020  
Social Service Student, Undergaduate Student. Facultad de Ciencias, UNAM
03/2020  
Social Service Student, Undergaduate Student. Facultad de Ciencias, UNAM
03/2020  
Social Service Student, Undergaduate Student. Facultad de Ciencias, UNAM
03/2020  
Social Service Student, Undergaduate Student. Facultad de Ciencias, UNAM

Projects

*

SIHSedesa: Hospital Information System - SEDESA

The aim of the project is to develop a hospital information system that includes a respiratory triage module, automatic data import module from health recodrs, identification of relevant terms from medical records, and visualization with dashboards.

PAPIIT TA100520: Authorship analysis on documents with deep learning techniques.

The aim of the project is to develop methods that allow the extraction of relevant feature from documents for authorship analysis, using deep neural architectures that allow to obtain lexical, syntactic, and semantic properties of texts.

CONACYT Project 298036: Feria de Talleres Mexicanas del Futuro: Trazando conciencias, pensando en TI Edición IIMAS UNAM.

The project aims at promoting the scientific-technological vocation among female students of UNAM’s highschool. For this, we invite the girls to study a science and technology career through conferences and workshops in a fun and interesting environment to show them that thinking that women and technology do not get along is an unfounded prejudice. We held a workshop fair at UNAM campus. Worshops and talks were given by professional women from the world of academy and industry, focused on the student population of the UNAM.

Lexical resource for data processing of social networks

The aim of the project is the collection of dictionaries of slang words, contractions, abbreviations and emoticons commonly used in social media. The diccitionaries are in English, Spanish, Dutch, and Italian languages.

Spanish NewsCorpus: Multi-tagged corpus for authorship analysis in Spanish

The aim of the project is the compilation of news in Spanish from digital media sites and its categorization into three areas: variation of Spanish, author, and author’s gender. The collection was carried out semi-automatically with a web crawler developed for this purpose.

Recent Publications

Quickly discover relevant content by filtering publications.
(2020). Siamese Network applied to Authorship Verification. Working Notes of CLEF.

PDF

(2020). Descriptions of issues and comments for predicting issue success in software projects. Journal of Systems and Software.

PDF

(2020). Enhancing Job Searches in Mexico City with Language Technologies. Proceedings of the 1st Workshop on Language Technologies for Government and Public Administration (LT4Gov).

PDF

(2020). Gender Identification in Social Media Using Transfer Learning. Mexican Conference on Pattern Recognition.

PDF Project

(2020). “Bend the truth”: Benchmark dataset for fake news detection in urdu language and its evaluation. Journal of Intelligent & Fuzzy Systems.

PDF

Contact