What Else Would I Like? A User Simulator using Alternatives for Improved Evaluation of Fashion Conversational Recommendation Systems

TL;DR

This paper introduces an enhanced user simulator for fashion conversational recommendation systems that considers alternative items and user patience, leading to more accurate offline evaluation of CRS effectiveness.

Contribution

It proposes a novel user simulator that incorporates alternative items and user patience, addressing limitations of single-target evaluation methods in CRS.

Findings

Alternative-aware simulators significantly impact CRS evaluation results.

Allowing users to consider alternatives shows CRS can satisfy users more quickly.

Single-target evaluation underestimates CRS effectiveness.

Abstract

In Conversational Recommendation Systems (CRS), a user can provide feedback on recommended items at each interaction turn, leading the CRS towards more desirable recommendations. Currently, different types of CRS offer various possibilities for feedback, i.e., natural language feedback, or answering clarifying questions. In most cases, a user simulator is employed for training as well as evaluating the CRS. Such user simulators typically critique the current retrieved items based on knowledge of a single target item. Still, evaluating systems in offline settings with simulators suffers from problems, such as focusing entirely on a single target item (not addressing the exploratory nature of a recommender system), and exhibiting extreme patience (consistent feedback over a large number of turns). To overcome these limitations, we obtain extra judgements for a selection of alternative items in common CRS datasets, namely Shoes and Fashion IQ Dresses. Going further, we propose improved user simulators that allow simulated users not only to express their preferences about alternative items to their original target, but also to change their mind and level of patience. In our experiments using the relative image captioning CRS setting and different CRS models, we find that using the knowledge of alternatives by the simulator can have a considerable impact on the evaluation of existing CRS models, specifically that the existing single-target evaluation underestimates their effectiveness, and when simulated users are allowed to instead consider alternatives, the system can rapidly respond to more quickly satisfy the user.