Beyond DCG: user behavior as a predictor of a successful search
- Ahmed Hassan Awadallah, R. Jones, K. Klinkner
- Computer ScienceWeb Search and Data Mining
- 4 February 2010
This work shows empirically that user behavior alone can give an accurate picture of the success of the user's web search goals, without considering the relevance of the documents displayed.
Modeling dwell time to predict click-level satisfaction
- Youngho Kim, Ahmed Hassan Awadallah, Ryen W. White, I. Zitouni
- Computer ScienceWeb Search and Data Mining
- 24 February 2014
It is shown that the topic of the page, its length and its readability level are critical in determining the amount of dwell time needed to predict whether any click is associated with satisfaction, and a method to model and provide a better understanding of click dwell time is proposed.
Automatic Online Evaluation of Intelligent Assistants
- Jiepu Jiang, Ahmed Hassan Awadallah, O. Khan
- Computer ScienceThe Web Conference
- 18 May 2015
This paper uses implicit feedback from users to predict whether users are satisfied with the intelligent assistant as well as its components, i.e., speech recognition and intent classification, and develops consistent and automatic approaches that can evaluate different tasks in voice-activated intelligent assistants.
Understanding and Predicting Graded Search Satisfaction
- Jiepu Jiang, Ahmed Hassan Awadallah, Xiaolin Shi, Ryen W. White
- Computer ScienceWeb Search and Data Mining
- 2 February 2015
This work is the first to study the problem of understanding and predicting graded (multi-level) search satisfaction and shows that its approach can predict subtle changes in search satisfaction more accurately than state-of-the-art methods, affording greater insight into search satisfaction.
Multi-Source Cross-Lingual Model Transfer: Learning What to Share
- Xilun Chen, Ahmed Hassan Awadallah, Hany Hassan, Wei Wang, Claire Cardie
- Computer ScienceAnnual Meeting of the Association for…
- 8 October 2018
This model leverages adversarial networks to learn language-invariant features, and mixture-of-experts models to dynamically exploit the similarity between the target language and each individual source language to further boost target language performance.
Uncertainty-aware Self-training for Few-shot Text Classification
- Subhabrata Mukherjee, Ahmed Hassan Awadallah
- Computer ScienceNeural Information Processing Systems
- 29 June 2020
This work proposes an approach to improve self-training by incorporating uncertainty estimates of the underlying neural network leveraging recent advances in Bayesian deep learning and proposes acquisition functions to select instances from the unlabeled pool leveraging Monte Carlo (MC) Dropout and learning mechanism leveraging model confidence for self- training.
Identifying Text Polarity Using Random Walks
- Ahmed Hassan Awadallah, Dragomir R. Radev
- Computer ScienceAnnual Meeting of the Association for…
- 11 July 2010
A Markov random walk model is applied to a large word related-ness graph, producing a polarity estimate for any given word, and outperforms the state of the art methods in the semi-supervised setting.
Struggling or exploring?: disambiguating long search sessions
- Ahmed Hassan Awadallah, Ryen W. White, S. Dumais, Yi-Min Wang
- Computer ScienceWeb Search and Data Mining
- 24 February 2014
This paper analyzes struggling and exploring behavior in Web search using log data from a commercial search engine, and builds classifiers that can accurately distinguish between exploring and struggling sessions using behavioral and topical features.
Understanding User Satisfaction with Intelligent Assistants
- Julia Kiseleva, Kyle Williams, T. Anastasakos
- Computer ScienceConference on Human Information Interaction and…
- 13 March 2016
A user study designed to measure user satisfaction over a range of typical scenarios of use is described, finding that the notion of satisfaction varies across different scenarios, and that overall task-level satisfaction cannot be reduced to query- level satisfaction alone.
Enhancing personalized search by mining and modeling task behavior
- Ryen W. White, Wei Chu, Ahmed Hassan Awadallah, Xiaodong He, Yang Song, Hongning Wang
- Computer ScienceThe Web Conference
- 13 May 2013
A method whereby other users performing similar tasks to the current user and leverage their on-task behavior to identify Web pages to promote in the current ranking yields promising gains in retrieval performance, and has direct implications for improving personalization in search systems.
...
...