I'm a Postdoctoral researcher at the University of Copenhagen. I work in the Natural Language Processing Section at the Department of Computer Science and am part of CoAStal, a Natural Language Processing Research group. My research interests lie within assessing fairness in models and model explainability.
Originally from México and the U.S. (yes, both), I am currently living in Denmark. Beyond my academic interests, I love to run, swim, travel, play ukulele, read fiction, history, among many other things.
Languages
English
Spanish
Danish
Resume
Education
PhD. in Machine Learning and Natural Language Processing
Dissertation title: Human-Centered Natural Language Processing.
MSc. in Information Technology and Cognition
University of Copenhagen
Thesis dealt with the use of eye tracking data to improve Natural Language Processing systems. Work from my master thesis resulted in 2 publications.
BSc. in Cognitive Science and Neuroscience
University of California, San Diego (UCSD). During this time worked in Birch Aquarium and Reuben H. Fleet Science center.
Experience
AI Research Scientist at Halfspace
Postdoctoral Researcher at the University of Copenhagen
Continuing work on Explainable AI, human-centered AI, fairness in NLP
Research Intern at Facebook AI
Working in evaluation of explanations in open-domain question answering
Data Scientist at botXO
Worked in conversational chat bots for customer support. Collaboration with University of Copenhagen
Research Assistant at Center for Visual Cognition
Extracting and analyzing eye tracking data for a longitudinal study looking at motor function and attention throughout the period when children are learning to read, in order to isolate factors leading to reading and learning deficiencies.
Research Assistant at Language Cognition Lab
Conducting research looking at switching costs in Spanish/English bilinguals.
News
December 2020
I will be starting a postdoc in March 2021 at the University of Copenhagen. Excited to continue working on Explainable AI. Related to that, preprint of my latest project on Explainable AI available here!
September 2020
Our paper titled "Type B Reflexivization as an Unambiguous Testbed for Multilingual Multi-Task Gender Bias" was accepted at EMNLP 2020 . Currently working at Facebook
August 2020
Teaching course for the NLP summer school organized by the Mexican Association of NLP
July 2020
1 paper submitted at EMNLP 2020 and 1 paper submitted at CONLL 2020
February 2020
Will be joining Facebook AI in the fall of 2020 as a research intern, at Menlo Park.
January 2020
Giving a talk at the FemTech workshop, at the University of Copenhagen.
November 2019
2 papers accepted at the Conversational AI workshop, at NeurIPS 2019
August 2019
1 paper accepted at EMNLP 2019 , held in Hong Kong.
April 2019
The first Women in Data Science Conference held in Copenhagen. (Part of the organizing committee)
February 2019
Participated in the emotional context shared task at 13th International Workshop on Semantic Evaluation.
January 2019
Participated in the Doctoral Consortium at AAAI 2019, held in Honolulu, Hawaii.
Publications
2021
Gonzalez, Ana Valeria; Rogers, Anna; Søgaard, Anders. 2021. On the Interaction of Belief Bias and Explanations. Findings of The 59th Annual Meeting of the Association for Computational Linguistics (ACL). Virtual conference.
Gonzalez, Ana Valeria; Bansal, Gagan; Fan, Angela; Mehdad, Yashar; Jia, Robin; Iyer, Srinivasan. 2021. Do Explanations Help Users Detect Errors in Open-Domain QA? An Evaluation of Spoken vs. Visual Explanations. Findings of The 59th Annual Meeting of the Association for Computational Linguistics (ACL). Virtual conference.
2020
Gonzalez, Ana Valeria; Søgaard, Anders. 2020. The Reverse Turing Test for Evaluating Interpretability Methods on Unknown Tasks. NeurIPS Workshop on Human And Machine in-the-Loop Evaluation and Learning Strategies. Virtual conference.
Gonzalez, Ana Valeria; Barrett, Maria; Hvingelby, Rasmus; Webster, Kellie; Søgaard, Anders. 2020. Type B Reflexivization as an Unambiguous Testbed for Multilingual Multi-Task Gender Bias. Conference on Empirical Methods in Natural Language Processing (EMNLP) 2020. Punta Cana, Dominican Republic.
2019
González, Ana Valeria; Augenstein, Isabelle; Søgaard, Anders. 2019. Retrieval-based goal-directed dialogue generation. The 3rd NeurIPS workshop on Conversational AI: Today’s Practice and Tomorrow’s Potential. Vancouver, Canada.
Bingel, Joachim; Petrén Bach Hansen, Victor; González, Ana Valeria; Budzianowski, Pavel; Augenstein, Isabelle; Søgaard, Anders. 2019. Domain Transfer in Dialogue Systems without Turn-Level Supervision. The 3rd NeurIPS workshop on Conversational AI: Today’s Practice and Tomorrow’s Potential. Vancouver, Canada.
Aralikatte, Rahul; Lent, Heather; Gonzalez, Ana Valeria; Herschcovich, Daniel; Qiu, Chen; Sandholm, Anders; Ringgaard, Michael; Søgaard, Anders. Rewarding Coreference Resolvers for Being Consistent with World Knowledge. Conference on Empirical Methods in Natural Language Processing (EMNLP) 2019. Hong Kong, China.
Beloucif, Meriem; González, Ana Valeria; Bollmann, Marcel; Søgaard, Anders. 2019. Naive regularizers for low-resource neural machine translation. Recent Advances in Natural Language Processing 2019. Borovets, Bulgaria.
González, Ana Valeria; Petrén Bach Hansen, Victor; Bingel, Joachim; Søgaard, Anders. 2019. CoAStaL at SemEval-2019 Task 3: Affect Classification in Dialogue using Attentive BiLSTMs. The 13th International Workshop on Semantic Evaluation (SemEval). Minneapolis, Minnesota.
2018
González, Ana Valeria; Augenstein, Isabelle; Søgaard, Anders. 2018. A strong baseline for question relevancy ranking. Conference on Empirical Methods in Natural Language Processing (EMNLP) 2018. Brussels, Belgium.
Barrett, Maria; Frermann, Lea; González, Ana Valeria; Søgaard, Anders. 2018. Unsupervised induction of linguistic categories with records of reading, speaking, and writing. North American Chapter of the Association for Computational Linguistics (NAACL). New Orleans, Louisiana.
González, Ana Valeria; Søgaard, Anders. 2018. Learning to predict readability using eye-movement data from natives and learners. The 32nd AAAI Conference on Artificial Intelligence (AAAI). New Orleans, Louisiana.
2017
González, Ana Valeria; Søgaard, Anders. 2017. Using gaze to predict text readability. 12th Workshop on Innovative Use of NLP for Building Educational Applications, EMNLP 2017. Copenhagen, Denmark.
González, Ana Valeria; Søgaard, Anders. 2017. Using gaze data to evaluate text readability: a multi-task learning approach. 19th European Conference on Eye Movements (ECEM). Wuppertal, Germany.
My Blog
March 19, 2018
100 Ways to be more happy
March 19, 2018
Tips to losing more weight
March 19, 2018
100 Ways to be more happy
March 19, 2018
Tips to losing more weight
March 19, 2018
100 Ways to be more happy
March 19, 2018
Tips to losing more weight
Contact Me
Get in Touch
If you are interested in collaboration, want to exchange ideas, or have any other professional inquiries, feel free to send me a message!