Search Results for author: Milagro Teruel

Found 8 papers, 5 papers with code

On Improving Summarization Factual Consistency from Natural Language Feedback

1 code implementation20 Dec 2022 Yixin Liu, Budhaditya Deb, Milagro Teruel, Aaron Halfaker, Dragomir Radev, Ahmed H. Awadallah

We collect a high-quality dataset, DeFacto, containing human demonstrations and informational natural language feedback consisting of corrective instructions, edited summaries, and explanations with respect to the factual consistency of the summary.

Text Generation Zero-Shot Learning

Legal NERC with ontologies, Wikipedia and curriculum learning

no code implementations EACL 2017 Cristian Cardellino, Milagro Teruel, Laura Alonso Alemany, Serena Villata

We find that this classifier works well in the Wikipedia, but, as could be expected, performance decreases in a corpus of judgments of the European Court of Human Rights.

Dependency Parsing Semantic Role Labeling

Improving Grounded Language Understanding in a Collaborative Environment by Interacting with Agents Through Help Feedback

no code implementations21 Apr 2023 Nikhil Mehta, Milagro Teruel, Patricio Figueroa Sanz, Xin Deng, Ahmed Hassan Awadallah, Julia Kiseleva

We explore multiple types of help players can give to the AI to guide it and analyze the impact of this help in AI behavior, resulting in performance improvements.

Cannot find the paper you are looking for? You can Submit a new open access paper.