Building Task-Oriented Dialogue Systems for Online Shopping

TLDR

This pioneering work demonstrates how existing NLP techniques, data resources, and crowdsourcing can be leveraged to build task‑oriented dialogue systems for e‑commerce. The study presents a general solution to build task‑oriented dialogue systems for online shopping that assist customers in completing purchase‑related tasks through natural language conversation, and identifies future challenges. The authors develop a system integrating existing NLP methods and crowdsourced data, and deploy it within a mobile online shopping app to demonstrate effectiveness. The deployed Chinese AI bot is the first of its kind to be used by millions of real consumers in online shopping, and analysis of human‑bot logs reveals interesting observations.

Abstract

We present a general solution towards building task-oriented dialogue systems for online shopping, aiming to assist online customers in completing various purchase-related tasks, such as searching products and answering questions, in a natural language conversation manner. As a pioneering work, we show what & how existing NLP techniques, data resources, and crowdsourcing can be leveraged to build such task-oriented dialogue systems for E-commerce usage. To demonstrate its effectiveness, we integrate our system into a mobile online shopping app. To the best of our knowledge, this is the first time that an AI bot in Chinese is practically used in online shopping scenario with millions of real consumers. Interesting and insightful observations are shown in the experimental part, based on the analysis of human-bot conversation log. Several current challenges are also pointed out as our future directions.