Search Results for author: Oana Inel

Found 12 papers, 7 papers with code

Adversarial Nibbler: An Open Red-Teaming Method for Identifying Diverse Harms in Text-to-Image Generation

1 code implementation14 Feb 2024 Jessica Quaye, Alicia Parrish, Oana Inel, Charvi Rastogi, Hannah Rose Kirk, Minsuk Kahng, Erin Van Liemt, Max Bartolo, Jess Tsang, Justin White, Nathan Clement, Rafael Mosquera, Juan Ciro, Vijay Janapa Reddi, Lora Aroyo

By focusing on ``implicitly adversarial'' prompts (those that trigger T2I models to generate unsafe images for non-obvious reasons), we isolate a set of difficult safety issues that human creativity is well-suited to uncover.

Text-to-Image Generation

Collect, Measure, Repeat: Reliability Factors for Responsible AI Data Collection

1 code implementation22 Aug 2023 Oana Inel, Tim Draws, Lora Aroyo

We argue that data collection for AI should be performed in a responsible manner where the quality of the data is thoroughly scrutinized and measured through a systematic set of appropriate metrics.


Humans disagree with the IoU for measuring object detector localization error

1 code implementation28 Jul 2022 Ombretta Strafforello, Vanathi Rajasekart, Osman S. Kayhan, Oana Inel, Jan van Gemert

Our work is the first to evaluate IoU with humans and makes it clear that relying on IoU scores alone to evaluate localization errors might not be sufficient.

Operationalizing Framing to Support Multiperspective Recommendations of Opinion Pieces

no code implementations15 Jan 2021 Mats Mulder, Oana Inel, Jasper Oosterman, Nava Tintarev

We apply this notion to a re-ranking of topic-relevant recommended lists, to form the basis of a novel viewpoint diversification method.

Recommendation Systems Re-Ranking

A Survey of Crowdsourcing in Medical Image Analysis

no code implementations25 Feb 2019 Silas Ørting, Andrew Doyle, Arno van Hilten, Matthias Hirth, Oana Inel, Christopher R. Madan, Panagiotis Mavridis, Helen Spiers, Veronika Cheplygina

Despite the growing popularity of this approach, there has not yet been a comprehensive literature review to provide guidance to researchers considering using crowdsourcing methodologies in their own medical imaging analysis.

CrowdTruth 2.0: Quality Metrics for Crowdsourcing with Disagreement

2 code implementations18 Aug 2018 Anca Dumitrache, Oana Inel, Lora Aroyo, Benjamin Timmermans, Chris Welty

However, in many domains, there is ambiguity in the data, as well as a multitude of perspectives of the information examples.

Human-Computer Interaction Social and Information Networks

Crowdsourcing StoryLines: Harnessing the Crowd for Causal Relation Annotation

1 code implementation COLING 2018 Tommaso Caselli, Oana Inel

This paper describes a crowdsourcing experiment on the annotation of plot-like structures in English news articles.

Relation valid

Temporal Information Annotation: Crowd vs. Experts

no code implementations LREC 2016 Tommaso Caselli, Rachele Sprugnoli, Oana Inel

This paper describes two sets of crowdsourcing experiments on temporal information annotation conducted on two languages, i. e., English and Italian.

General Classification

Crowdsourcing Salient Information from News and Tweets

no code implementations LREC 2016 Oana Inel, Tommaso Caselli, Lora Aroyo

On the other hand, machines need to understand the information that is published in online data streams and generate concise and meaningful overviews.

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