Diego Garcia-Olanoresume | github | linkedin | twitter | publications | old site
I'm a PhD researcher interested in explainable NLP/ML for social good ( healthcare/public policy/general knowledge )
and have had my research published in ACL, ICML, IJCAI, CoNLL, ECML amongst other venues.
Expected Graduation Summer 2022 and actively looking for job opportunities in NLP/ML research starting in Fall 2022
I'm currently a 5th year PhD candidate in Electrical & Computer Engineering (ECE) at UT Austin
working with Dr. Joydeep Ghosh's IDEAL lab and Dr. Paydayfar's group at Dell Medical School.
My research interests broadly involve explaining Machine Learning model decisions on Natural Language and sequential data, and learning representations of entities and political networks for downstream tasks. My PhD proposal accepted in June 2021 by professors Joydeep Ghosh, Alex Dimakis, Harris Vikalo, Atlas Wang & Byron Wallace is titled "In-process Diagnostic methods for Entity Representation Learning on Sequential data at Scale" and focuses on methods that allow neural networks to be more transparent, explainable, and diagnosable during the process of learning and inference as opposed to in a post-hoc analysis fashion. My research has dealt with learning sparse interpretable biomedical text representations (ACL 21), dense entity retrieval using dual encoders (CoNLL 19), prototypical learning of time series data (ICML 19(short) IJCAI 19 (long)), amongst other things. I'm currently looking at knowledge injection for the Knowledge Aware Visual Question Answering task where external world knowledge about entities is required for obtaining a correct response.
key words: interpretable entity representations, knowledge injection for multimodal VQA, dense retrieval, in-network prototype learning, dual encoders, feature importance methods, counterfactual explanations
Dec 2021, preprint on "Improving and Diagnosing Knowledge-Based Visual Question Answering via Entity Enhanced Knowledge Injection" is available. Paper || Code
Summer 2021, my PhD Proposal on "In-process Diagnostic methods for Entity Representation Learning on Sequential Data" has been accepted for candidacy.
Our paper "Biomedical Interpretable Entity Representations" has been accepted at ACL-ICJNLP 2021. Paper || Code || Slides
For the Summer 2020, I have been selected to be an IBM Research PhD fellow for Social Good and will work on a Drug Repurposing for Cancer project using NLP.
I recently gave a high level talk to Cognitive Scale on Explainable AI for NLP (slides link).
In Summer 2019, I interned at Google Cloud AI in Seattle with Besim Avci working on explaining seq2seq models using feature attribution methods on Transformer and LSTM based architectures with attention for machine translation.
In Spring 2019: I was a TA for Responsible AI Graduate Seminar ( lots of papers and presentations on Explainability, Fairness, etc!)
In Summer 2018, I interned at Google Research in Mountain View with Jason Baldridge working on entity linking.
In Fall 2017: I started at UT and was a TA for an Advanced Data Mining Masters course.
In Summer 2016, I was selected as an Eric & Wendy Schmidt Data Science for Social Good 2016 fellow at the Unviersity of Chicago and worked with SEDESOL of Mexico on improving their distribution of social services.
I obtained a Masters of Data Science at the UPC in Barcelona in July 2015 (masters thesis on automated construction of political networks).
I have a bachelors in Computer Science, Political Science and Hispanic Studies with a Business minor from UT Austin.
A selection of publications and projects, academic, professional and personal.
|Biomedical Interpretable Entity Representations (ACL 21)
-- Paper || Code || Slides
|Improving and Diagnosing Knowledge-Based
Visual Question Answering via Entity Enhanced Knowledge Injection
-- Paper (arxiv) || Code
|Learning Dense Representations for Entity Retrieval (CONLL 19)
-- Paper || Code
|Explaining Deep Classification of Time-Series Data with Learned Prototypes (ICML 19 Timeseries Workshop 4pgs)
-- Paper || Code
IJCAI 19 Knowledge and Health Discovery Long paper
-- Paper || Code
|Applying Machine Learning Methods to Enhance the Distribution of Social Services in Mexico (ARXIV 2017)|
|Automated construction and analysis of political networks via open government & media sources (ECML 16)|
|Link Detection in Political Networks (NLP Class Project 2018)|
|Predicting a Politician's Party Affiliation from a Photo using Deep Learning Methods ( Deep Learning Class project 2017)|
|Predicting when a Yearbook Photo was Taken using Convolutional Neural Networks|
|Pitchfork: Are music festival lineups getting worse?|
|Glasstire 15th Year Anniversary Texas Art Events|
|Assessment of Similarity in Central and State Climate Change Programs of Mexico (Simultec Special Session on Applications of Modeling and Simulation to Climatic Change and Environmental Sciences. 2015)|
|Glasstire 15th Year Contributors|
|Glasstire 15th Year Texas Artists|
|Personal Music Visualizations and Interactive Lists|
|Turning Album of the Year Lists into a Music Discovery Tool|
|Looking at US Presidential Election County Changes from 2012 to 2016|
|Blue Islands Project
Identify Blue Counties in America that are surrounded by Red ones, and Predict if a county is a blue island based on just socio-economic and public health data.
|Google Results By Country|
|Every Foreign Film Ever Nominated for the Oscars|
|My Favorite Painter's Colors|
|Groove Is In The Heart|
|Songs of Summer Jobs||'|
How Music Crosses American Borders
|There Are Three Types of Gun Songs|
|The Persistent Glass Ceiling of Music|
|From a Benzo to Student Loans:
Debt Anxiety in Today’s Pop Music
|Hot Time, Summer in the City|
|Extended Politician Networks|
|Topics and Table of Contents|
|Media Coverage Maps|
|More Media Coverage Results|