-
Task-based support in search engines
This was a very particular talk… my PhD Viva! In 45 minutes, I summarized my work spanning over more than 3 years in the problem of supporting task completion in web search. (If your browser doesn't support slideshowing, you can view it on SlideShare: Task-Based Support in Search Engines.)
-
Unsupervised context retrieval for long-tail entities
This talk presented our work in the context of monitoring entities, like persons and companies, in news streams. We study the problem of retrieving, in an unsupervised fashion, textual contexts that can support the acquisition of labeled data to train machine learning models for entity linking. We developed this project...
-
Task recommendation
A Symposium at the IAI group in Stavanger held my talk about our work on task recommendation. This is a set of two novel problems designed to better study the problem of supporting task-completion in web search engines. Additionally to introducing these problems, we develop datasets and approaches for recommending...
-
About "Towards better text understanding and retrieval through kernel entity salience modeling"
This summary of the article Towards Better Text Understanding and Retrieval through Kernel Entity Salience Modeling, by Xiong, Liu, Callan and Liu (accepted at SIGIR 2018), was presented at a reading group during my internship at Signal in London. (If your browser doesn't support slideshowing, you can view it on...