Search Results for author: Aaron Halfaker

Found 9 papers, 3 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

Effects of algorithmic flagging on fairness: quasi-experimental evidence from Wikipedia

no code implementations4 Jun 2020 Nathan TeBlunthuis, Benjamin Mako Hill, Aaron Halfaker

We propose that algorithmic flagging systems deployed to improve the efficiency of moderation work can also make moderation actions more fair to these users by reducing reliance on social signals and making norm violations by everyone else more visible.


ORES: Lowering Barriers with Participatory Machine Learning in Wikipedia

1 code implementation11 Sep 2019 Aaron Halfaker, R. Stuart Geiger

Algorithmic systems---from rule-based bots to machine learning classifiers---have a long history of supporting the essential work of content moderation and other curation work in peer production projects.

BIG-bench Machine Learning

PreCall: A Visual Interface for Threshold Optimization in ML Model Selection

no code implementations11 Jul 2019 Christoph Kinkeldey, Claudia Müller-Birn, Tom Gülenman, Jesse Josua Benjamin, Aaron Halfaker

In this paper we present PreCall, an interactive visual interface for ORES, a machine learning-based web service for Wikimedia projects such as Wikipedia.

BIG-bench Machine Learning Model Selection

Identifying Semantic Edit Intentions from Revisions in Wikipedia

no code implementations EMNLP 2017 Diyi Yang, Aaron Halfaker, Robert Kraut, Eduard Hovy

Most studies on human editing focus merely on syntactic revision operations, failing to capture the intentions behind revision changes, which are essential for facilitating the single and collaborative writing process.

Information Retrieval Lexical Simplification +2

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