Xi Wang

A lecturer (~Assistant Professor) of Natural Language Processing at The University of Sheffield (TUoS) with research interests in Interactive NLP, Conversational AI, and personalisation as well as relevant topics among Natural Language Processing (NLP) and Information Retrieval (IR). Before joining the University of Sheffield, I obtained my PhD from the University of Glasgow, supervised by Prof. Iadh Ounis and Prof. Craig Macdonald and focusing on the research topic of developing review-based recommender systems. After that, I joined the web intelligence group of University College London (UCL) as a postdoctoral researcher, supervised by Prof. Emine Yilmaz and working on Task-oriented Dialogue Systems. My existing works have been published in top-tier international NLP and IR conferences, including ACL, EMNLP, AAAI, SIGIR, CIKM, WWW and ECIR. During the postdoctoral research period, joined with Prof. Emine Yilmaz, a research grant was awarded by Google for developing Knowledge-enriched task-oriented dialogue systems.
I am actively looking for PhD students to work on topics related to proactive conversational information seeking, retrieval augmented generation and user simulation. If you are interested, please drop an email to xi.wang[at]sheffield.ac.uk with the subject starts with [PhD 2026].
news
Dec 1, 2023 | Paper “A Social-aware Gaussian Pre-trained Model for Effective Cold-start Recommendation” accepted to the journal of Information Processing & Management (IP&M). |
---|---|
Oct 7, 2023 | Paper “Improving Conversational Recommendation Systems via Bias Analysis and Language-Model-Enhanced Data Augmentation” accepted to EMNLP 2023 (Findings). |
Jan 7, 2023 | Co-first authored paper “A Survey on Asking Clarification Questions Datasets in Conversational Systems” accepted to ACL 2023 (main). |
Nov 1, 2022 | Received Google research workshop grant on Action, Task and User Journey ($20,000) as Co-recipient with Prof. Emine Yilmaz. |
Oct 1, 2022 | Co-first authored paper “Task2KB: A Public Task-Oriented Knowledge Base” accepted to AAAI 2023. |