Efficient Large-Scale Domain Classification with Personalized Attention

By Young-Bum Kim, Dongchan Kim, Anjishnu Kumar, Ruhi Sarikaya. 2018

20 citations recorded by the source corpus.

In this paper, we explore the task of mapping spoken language utterances to one of thousands of natural language understanding domains in intelligent personal digital assistants (IPDAs). This scenario is observed for many mainstream IPDAs in industry that allow third parties to develop thousands of new domains to augment built-in ones to rapidly increase domain coverage and overall IPDA capabilities. We propose a scalable neural model architecture with a shared encoder, a novel attention mechanism that incorporates personalization information and domain-specific classifiers that solves the problem efficiently. Our architecture is designed to efficiently accommodate new domains that appear in-between full model retraining cycles with a rapid bootstrapping mechanism two orders of magnitude faster than retraining. We account for practical constraints in real-time production systems, and design to minimize memory footprint and runtime latency. We demonstrate that incorporating personalization results in significantly more accurate domain classification in the setting with thousands of overlapping domains.

Subfields: Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Minlie Huang
2. Jinsik Lee
3. Hwaran Lee
4. Joo-Kyung Kim
5. Tae-Yoon Kim
6. Guanyi Chen
7. Young-Bum Kim
8. Yinhe Zheng

Citations in the corpus

• Out-of-Domain Detection for Natural Language Understanding in Dialog Systems (2019, background): “2983593 network-based NLU models are proposed, and some of these models have been applied in real-world applications [1]–[3].”
• Joint Learning of Domain Classification and Out-of-Domain Detection with Dynamic Class Weighting for Satisficing False Acceptance Rates (2018, background): “In real spoken dialog systems, the classification performance can be further improved by leveraging various contextual information [32, 33, 34, 26].”
• SUMBT: Slot-Utterance Matching for Universal and Scalable Belief Tracking (2019, methodology): “For example, as reported by Kim et al. (2018), hundreds of new skills are added per week in personal assistant services.”