Hello! I am Danilo Ribeiro.
I'm currently a PhD candidate at Northwestern University. The goal of my research is to build intelligent agents that are able to incorporate knowledge and reasoning when processing natural language, either by enhancing current NLP systems or by creating innovative ways of learning and applying knowledge to solve language tasks.
daniloneves.web@gmail.com
2017 - Current
Computer Science - PhD Candidate
My current research focus includes natural language understanding, question answering, knowledge extraction, dialogue systems, reasoning and data efficient learning.
Advisor: Ken Forbus
2013 - 2014
Bachelor of Computer Science - Visiting Student
Activities: Programming team - every week we solved challenging programming problems to prepare for ACM ICPC competition. This helped sharp my programming skill as well as working in a team to solve computational problems.
2011 - 2015
Bachelor of Computer Science
Graduated Magna Cum Laude. Best grades out of all other CS graduates.
Activities: Member of Programa de Educacao Tutorial (Mentorship program) governed funded selective group of undergraduate students. Tutor of Introduction to Algorithms. Member of time maratona (programming team).
ICLR - 2023
STREET is a unified multi-task and multi-domain natural language reasoning and explanation benchmark. Unlike most existing question-answering (QA) datasets, models are expected to not only answer questions, but also produce step-by-step structured explanations describing how premises in the question are used to produce intermediate conclusions that can prove the correctness of a certain answer.
NAACL - 2022
Structured explanations, called entailment trees, were recently suggested as a way to explain and inspect a QA system's answer. In order to better generate such entailment trees, we propose an architecture called Iterative Retrieval-Generation Reasoner (IRGR). Our model is able to explain a given hypothesis by systematically generating a step-by-step explanation from textual premises.
ACS - 2019
Many of the changes in the world that happen over time are characterized by processes. Creating programs that comprehend procedural text (e.g. the stages of photosynthesis) is a crucial task in natural language understanding. In this paper we present a novel approach that uses analogical question answering to predict what state changes affect entities in a paragraph describing a process.