Deep Cascade Multi-task Learning for Slot Filling in Online Shopping Assistant

TL;DR

This paper introduces a novel multi-task cascade model with residual connections for slot filling in E-commerce dialog systems, significantly improving accuracy over existing methods and deployed successfully in a real platform.

Contribution

The paper proposes a new multi-task cascade and residual network architecture tailored for E-commerce slot filling, outperforming traditional models and achieving real-world deployment.

Findings

14.6% F1 score improvement over baseline

130% accuracy increase in online testing

Effective on both new E-commerce and standard datasets

Abstract

Slot filling is a critical task in natural language understanding (NLU) for dialog systems. State-of-the-art approaches treat it as a sequence labeling problem and adopt such models as BiLSTM-CRF. While these models work relatively well on standard benchmark datasets, they face challenges in the context of E-commerce where the slot labels are more informative and carry richer expressions. In this work, inspired by the unique structure of E-commerce knowledge base, we propose a novel multi-task model with cascade and residual connections, which jointly learns segment tagging, named entity tagging and slot filling. Experiments show the effectiveness of the proposed cascade and residual structures. Our model has a 14.6% advantage in F1 score over the strong baseline methods on a new Chinese E-commerce shopping assistant dataset, while achieving competitive accuracies on a standard dataset. Furthermore, online test deployed on such dominant E-commerce platform shows 130% improvement on accuracy of understanding user utterances. Our model has already gone into production in the E-commerce platform.