Distant Supervision for Information Retrieval

distant_supervision.png

Search engines often require large-scale training data to improve their services. My Ph.D. dissertation at UMass (expected to finish in Summer 2018) studies automatic methods for generating such training data using public and unlabeled corpora. The proposed techniques make it possible to train cutting-edge retrieval techniques without Google-scale data.


Faithful Evaluation of Search and Conversational Systems

 Assessing user satisfaction with Microsoft Cortana based on action transition.

Assessing user satisfaction with Microsoft Cortana based on action transition.

I develop techniques to evaluate user experience in search and other systems automatically in real-time based on behavioral signals and user modeling. My work has been applied to evaluate user satisfaction with Bing and Microsoft Cortana.

More details ...


Interactive Search Behavior & Systems

A hypothetical relationship between the acquired amount of useful information, the effort spent, and the efficiency of acquiring useful information (Jiang et al., CHIIR '17).

I study human behavior in search and conversational systems based on search logs or laboratory user studies. I also design intelligent interactive search systems that are adaptive to users' potential behavior, including both promoting beneficial activities and avoiding harmful ones.

More details ...


Scholarly Data Analytics, Bibliometrics, and Scholarly Information Access

Connections of 25 disciplines based on online academic information sharing among 34K Mendeley groups, 61K members, and 12K followers (Jiang et al., JCDL '13).

I study techniques to help scientists and scholars better access and use academic information. I also collaborate with scholars in Informetrics and Science & Technology Studies to examine the connections of scholars and disciplines based on formal and informal scholarly activities.

More details ...