Search engines have difficulty searching into knowledge repositories since they are not tailored to the users' information needs. User's queries are, more often than not, under-specified that also retrieve irrelevant documents. Query refinement, also known as query reformulation or suggesetion, is the process of transforming users' queries into new refined versions without semantic drift to enhance the relevance of search results. Prior query refiners have been benchmarked on web retrieval datasets following weak assumptions that users' input queries improve gradually within a search session. To fill the gap, we contribute RePair, an open-source configurable toolkit to generate large-scale gold-standard benchmark datasets from a variety of domains for the task of query refinement.

1. Y. Lakshmi Narayanan, H. Fani; RePair: An Extensible Toolkit to Generate Large-Scale Datasets for Query Refinement via Transformers. In the 32nd ACM International Conference on Information and Knowledge Management, (CIKM'23), 2023.
   pdf doi git reviews

Within the context of review analytics, aspects are the features of products and services at which customers target their opinions and sentiments. Aspect detection helps product owners and service providers to identify shortcomings and prioritize customers' needs,and hence, maintain revenues and mitigate customer churn. Existing methods focus on detecting the surface form of an aspect by training supervised learning methods that fall short when aspects are latent in reviews. In this project, we propose methods to extract latent occurrences of aspects.

1. F. Hemmatizadeh, C. Wong^†, A. Yu⁺, H. Fani; LADy: A Benchmark Toolkit for Latent Aspect Detection Enriched with Backtranslation Augmentation. The 47th International ACM SIGIR Conference on Research and Development in Information Retrieval, (SIGIR'24), 2024.
   pdf doi git reviews
2. F. Hemmatizadeh, C. Wong^†, A. Yu⁺, H. Fani; Latent Aspect Detection via Backtranslation Augmentation. In the 32nd ACM International Conference on Information and Knowledge Management, (CIKM'23), 2023.
   pdf doi git reviews video
3. A. Mansouri, H. Fani; Latent Aspect Detection from Online Unsolicited Customer Reviews, 2022.
   pdf

Team Formation aims to automate forming teams of experts who can successfully solve difficult tasks. While state-of-the-art neural team formation methods are able to efficiently analyze massive collections of experts to form effective collaborative teams, they largely ignore the fairness in recommended teams of experts. Fairness breeds innovation and increases teams' success by enabling a stronger sense of community, reducing conflict, and stimulating more creative thinking. In Adila, we study the application of fairness-aware team formation algorithms to mitigate the potential biases in the neural team formation models.

1. H. Loghmani, H. Fani; Bootless Application of Greedy Re-ranking Algorithms in Fair Neural Team Formation. In the 4th International Workshop on Algorithmic Bias in Search and Recommendation, Colocated with the 45th European Conference on Information Retrieval (ECIR 2023), (BIAS'23), 2023.
   pdf git reviews video

Collaborative teams are the primary vehicle for coordinating experts with diverse skills needed for a particular collaborative project, and Team Formation (TF) has firsthand effects on creating organizational performance. We propose neural machine learning approaches to Team Formation. We will train neural models that would learn relationships among experts and their social attributes in vector space. Wherein, we consider all past (un)successful team compositions as training samples to predict future teams and the team's level of success. Therefore, we bring efficiency while enhancing efficacy due to the inherently iterative and online learning procedure in neural architectures.

1. M. Saeedi, C. Wong^†, H. Fani; Collaborative Team Recommendation for Skilled Users: Objectives, Techniques, and New Perspectives. In the 32nd ACM Conference on User Modeling, Adaptation and Personalization, (UMAP'24), 2024.
   pdf doi git reviews
2. H. Fani, R. Barzegar, A. Dashti, M. Saeedi; A Streaming Approach to Neural Team Formation Training. In the 46th European Conference on Information Retrieval, (ECIR'24), 2024.
   pdf doi git reviews ppt video
3. A. Dashti, S. Samet, H. Fani; Effective Neural Team Formation via Negative Samples. In the 31st ACM International Conference on Information and Knowledge Management, (CIKM'22), 2022.
   pdf doi git reviews
4. A. Dashti, K. Saxena, D. Patel^†, H. Fani; OpeNTF: A Benchmark Library for Neural Team Formation. In the 31st ACM International Conference on Information and Knowledge Management, (CIKM'22), 2022.
   pdf doi git reviews video
5. D. Patel^†, A. Dashti, K. Saxena, H. Fani; Automating Team Formation Using Machine Learning. Gold Medalist, CAD$300, UWill Discover, University of Windsor, 2022.
   link poster
6. K. Saxena, D. Patel^†, A. Dashti, H. Fani; Best Research, CAD$300, Demo Day, School of Computer Science, University of Windsor, 2022.
   

User community prediction aims at identifying communities in the future based on the users' temporal topics of interest. We model inter-user topical affinities at each time interval via streams of temporal graphs. We benefit from temporal graph embedding methods to learn temporal vector representations for users as users' topics of interests and hence their inter-user topical affinities are changing in time. We predict user communities in future time intervals based on the final locations of users' vectors in the latent space.

1. S. Ziaeinejad, S. Samet, H. Fani; SEERa: A Framework for Community Prediction. In the 31st ACM International Conference on Information and Knowledge Management, (CIKM'22), 2022.
   pdf doi git reviews video