paper-with-me

홈 › Papers

HERALD: An Annotation Efficient Method to Detect User Disengagement in Social Conversations

2021-06-01 · ACL 2021 5 · Weixin Liang, Kai-Hui Liang, Zhou Yu

Open-domain dialog systems have a user-centric goal: to provide humans with an engaging conversation experience. User engagement is one of the most important metrics for evaluating open-domain dialog systems, and could also be used as real-time feedback to benefit dialog policy learning. Existing work on detecting user disengagement typically requires hand-labeling many dialog samples. We propose HERALD, an efficient annotation framework that reframes the training data annotation process as a denoising problem. Specifically, instead of manually labeling training samples, we first use a set of labeling heuristics to label training samples automatically. We then denoise the weakly labeled data using the Shapley algorithm. Finally, we use the denoised data to train a user engagement detector. Our experiments show that HERALD improves annotation efficiency significantly and achieves 86% user disengagement detection accuracy in two dialog corpora.

📄 PDF Abstract BibTeX arXiv:2106.00162

Code (1)

Weixin-Liang/HERALD 공식 구현 pytorch

Tasks

DenoisingOpen-Domain Dialog

Similar Papers 제목 키워드 기반

Intrinsic and Extrinsic Evaluation of an Automatic User Disengagement Detector for an Uncertainty-Adaptive Spoken Dialogue System

2012-06-01 · NAACL 2012 6 · Kate Forbes-Riley, Diane Litman, Heather Friedberg, Joanna Drummond
Spoken Dialogue Systems

Stigma Annotation Scheme and Stigmatized Language Detection in Health-Care Discussions on Social Media

2020-05-01 · LREC 2020 5 · Nadiya Straton, Hyeju Jang, Raymond Ng

Much research has been done within the social sciences on the interpretation and influence of stigma on human behaviour and health, which result in out-of-group exclusion, distancing, cognitive separation, status loss, d…

Data Augmentation

Safeguarding Privacy: Privacy-Preserving Detection of Mind Wandering and Disengagement Using Federated Learning in Online Education

2026-02-10 · Anna Bodonhelyi, Mengdi Wang, Efe Bozkir, Babette Bühler 외 arxiv

Since the COVID-19 pandemic, online courses have expanded access to education, yet the absence of direct instructor support challenges learners' ability to self-regulate attention and engagement. Mind wandering and disen…

Federated Learning

Directed Social Regard: Surfacing Targeted Advocacy, Opposition, Aid, Harms, and Victimization in Online Media

2026-05-01 · Scott Friedman, Ruta Wheelock, Sonja Schmer-Galunder, Drisana Iverson 외 arxiv

The language in online platforms, influence operations, and political rhetoric frequently directs a mix of pro-social sentiment (e.g., advocacy, helpfulness, compassion) and anti-social sentiment (e.g., threats, oppositi…

Sentiment Analysis

SAVeD: A First-Person Social Media Video Dataset for ADAS-equipped vehicle Near-Miss and Crash Event Analyses

2025-12-19 · Shaoyan Zhai, Mohamed Abdel-Aty, Chenzhu Wang, Rodrigo Vena Garcia arxiv

The advancement of safety-critical research in driving behavior in ADAS-equipped vehicles require real-world datasets that not only include diverse traffic scenarios but also capture high-risk edge cases such as near-mis…

Monocular Depth EstimationSemantic SegmentationDomain Adaptation