SQuARE: Towards Multi-Domain and Few-Shot Collaborating Question Answering Agents


The exponential growth of Question Answering (QA) models and datasets is opening new application and research possibilities, such as modular and compositional systems. In this talk, we will present how to achieve multi-domain QA systems through the collaboration of multiple models. We will further explore how relevance feedback can be used for few-shot document re-ranking, and will finish by introducing UKP-SQuARE, the first online platform that provides an ecosystem for QA research. With UKP-SQuARE, users can deploy, run, analyze, and compare models with a standardized interface from multiple perspectives, such as general behavior, explainability, adversarial attacks, and behavioral tests, enabling a holistic analysis.


Haritz Puerto is a Ph.D. candidate in Machine Learning & Natural Language Processing at UKP Lab in TU Darmstadt, supervised by Prof. Iryna Gurevych. His main research interests are reasoning for Question Answering and Graph Neural Networks. Previously, he worked at the Coleridge Initiative, where he co-organized the Kaggle Competition Show US the Data. He got his master's degree from the School of Computing at KAIST, where he was a research assistant at IR&NLP Lab and was advised by Prof. Sung-Hyon Myaeng.

Open Data Science




Open Data Science
One Broadway
Cambridge, MA 02142

Privacy Settings
We use cookies to enhance your experience while using our website. If you are using our Services via a browser you can restrict, block or remove cookies through your web browser settings. We also use content and scripts from third parties that may use tracking technologies. You can selectively provide your consent below to allow such third party embeds. For complete information about the cookies we use, data we collect and how we process them, please check our Privacy Policy
Consent to display content from - Youtube
Consent to display content from - Vimeo
Google Maps
Consent to display content from - Google