TU Delft, Netherlands
I am a PhD student at TU Delft doing research on conversational search under the supervision of Claudia Hauff. I have BSc and MSc degrees from the Department of Computer Science (DCC) of UFMG - under the supervision of Rodrygo Santos. Before joining the PhD, I worked with machine learning and data science projects for 3 years at Hekima.
In the first year of my PhD I investigated neural ranking models for the conversation response ranking task. In particular models for information-seeking conversations: we created a novel dialogue corpus (MANtIS) of information-seeking conversations which has a few properties previous datasets lack. I developed and studied neural rankers inspired by techniques such as domain adaptation, curriculum learning and slice-based learning.
Before joining the PhD, my research was focused on performance prediction, i.e. predicting the effectiveness of models, for recommendation, document classification and adhoc retrieval (ECIR’19, Master thesis). When I was an undergrad I did research on scientific collaboration networks (JCBS, Scientometrics).
|Jan 26, 2020||Our paper on domain adaptation for conversation response ranking was accepted at CAIR’20.|
|Dec 20, 2019||The preprint of our ECIR’20 paper on curriculum learning for the conversation response ranking task is up.|
|Dec 11, 2019||We are releasing our new dataset of multi-domain information-seeking conversations called MANtIS!|