Natural language processing is becoming more and more important in recommender systems. This half day workshop explores challenges and potential research directions in Recommender Systems (RSs) combining Natural Language Processing (NLP). The focus will be on stimulating discussions around how to combine natural language processing technologies with recommendation. We will talk about theoretical, experimental, and methodological studies that leverage NLP technologies to advance recommender systems, as well as emphasize the applicability in practical applications. The workshop aims to bring together a diverse set of researchers and practitioners interested in investigating the interaction between NLP and RSs to develop more intelligent RSs.


08:30-08:40 Opening
08:40-9:25 Keynote (Jian-Yun Nie)
09:25-10:00 Invited talk (Julia Kiseleva)
10:00-10:30 Coffee break
10:30-11:15 Keynote (Julian McAuley)
11:20-11:50 Hands-on panel ( Jian-Yun Nie, Julia Kiseleva, Julian McAuley )


Jian-Yun Nie

University of Montreal
Title: Conversation in recommendation – opportunities and challenges
Abstract: Most current approaches to recommendation operate as a black box without explicit user interaction. A new form of interactive recommendation - conversational recommendation – is emerging in both industry and academia. In order to make recommendations, the system needs to interact with the user, through conversation, in order to determine the need of the user and to make good choices. In this talk, I will discuss what a conversational recommender can do beyond traditional systems, the possible approaches to be used, as well as the challenges.

Julian McAuley

UC San Diego
Title: Personalized Language Modeling, from Prediction to Generation and Justification
Abstract: I'll give a historical perspective on the use of NLP for recommendation, with a particular focus on personalized language generation. Examples include models for question answering, text and recipe generation, and interpretability. By personalizing these models, we are better able to adapt to both the preferences and the linguistic nuances of individuals.

Invited Talks

Julia Kiseleva

Microsoft Research AI
Title: Learning From Users Interactions
Abstract: Effective optimization is essential for interactive systems to provide a satisfactory user experience. However, it is often challenging to find an objective to optimize for. Generally, such objectives are manually crafted and rarely capture complex user needs accurately. Conversely, we will discuss how to infer the objective directly from observed user interactions. These inferences can be made regardless of prior knowledge and across different types of user behavior.


Xiao Huang

PhD student at Data Analytics at Texas A&M (DATA) Lab.

Pengjie Ren

Postdoctoral researcher at the Information and Language Processing Systems (ILPS) group, University of Amsterdam.

Zhaochun Ren

Professor at Shandong University.

Fei Sun

Algorithm expert in Search & Recommendation Group at Alibaba.

Xiangnan He

Professor with the University of Science and Technology of China (USTC).

Dawei Yin

Senior Director of Research at

Maarten de Rijke

University Professor of Artificial Intelligence and Information Retrieval at the University of Amsterdam