Jia Liu

Minghong Fang, Jia Liu, Michinari Momma et al.

Today, recommender systems have played an increasingly important role in shaping our experiences of digital environments and social interactions. However, as recommender systems become ubiquitous in our society, recent years have also witnessed significant fairness concerns for recommender systems. Specifically, studies have shown that recommender systems may inherit or even amplify biases from historical data, and as a result, provide unfair recommendations. To address fairness risks in recommender systems, most of the previous approaches to date are focused on modifying either the existing training data samples or the deployed recommender algorithms, but unfortunately with limited degrees of success. In this paper, we propose a new approach called fair recommendation with optimized antidote data (FairRoad), which aims to improve the fairness performances of recommender systems through the construction of a small and carefully crafted antidote dataset. Toward this end, we formulate our antidote data generation task as a mathematical optimization problem, which minimizes the unfairness of the targeted recommender systems while not disrupting the deployed recommendation algorithms. Extensive experiments show that our proposed antidote data generation algorithm significantly improve the fairness of recommender systems with a small amounts of antidote data.

Hongru Liang, Jia Liu, Weihong Du et al.

The machine reading comprehension (MRC) of user manuals has huge potential in customer service. However, current methods have trouble answering complex questions. Therefore, we introduce the Knowing-how & Knowing-that task that requires the model to answer factoid-style, procedure-style, and inconsistent questions about user manuals. We resolve this task by jointly representing the steps and facts in a graph TARA, which supports a unified inference of various questions. Towards a systematical benchmarking study, we design a heuristic method to automatically parse user manuals into TARAs and build an annotated dataset to test the model's ability in answering real-world questions. Empirical results demonstrate that representing user manuals as TARAs is a desired solution for the MRC of user manuals. An in-depth investigation of TARA further sheds light on the issues and broader impacts of future representations of user manuals. We hope our work can move the MRC of user manuals to a more complex and realistic stage.

Ziwei Cong, Jia Liu, Puneet Manchanda

A common belief about the growing medium of livestreaming is that its value lies in its "live" component. We examine this belief by comparing how the price elasticity of demand for live events varies before, on the day of, and after livestream. We do this using unique and rich data from a large livestreaming platform that allows consumers to purchase the recorded version of livestream after the stream is over. A challenge in our context is that there exist high-dimensional confounders whose relationships with treatment policy (i.e., price) and outcome of interest (i.e., demand) are complex and only partially known. We address this challenge via the use of a generalized Orthogonal Random Forest framework for heterogeneous treatment effect estimation. We find significant temporal dynamics in the price elasticity of demand over the entire event life-cycle. Specifically, demand becomes less price sensitive over time to the livestreaming day, turning to inelastic on that day. Over the post-livestream period, the demand for the recorded version is still sensitive to price, but much less than in the pre-livestream period. We further show that this temporal variation in price elasticity is driven by the quality uncertainty inherent in such events and the opportunity of real-time interaction with content creators during the livestream.