Kanna Shimizu


2023

pdf
Personalized Dense Retrieval on Global Index for Voice-enabled Conversational Systems
Masha Belyi | Charlotte Dzialo | Chaitanya Dwivedi | Prajit Muppidi | Kanna Shimizu
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: Industry Track

Voice-controlled AI dialogue systems are susceptible to noise from phonetic variations and failure to resolve ambiguous entities. Typically, personalized entity resolution (ER) and/or query rewrites (QR) are deployed to recover from these error modes. Previous work in this field achieves personalization by constraining retrieval search space to personalized indices built from user’s historical interactions with the device. While constrained retrieval achieves high precision, predictions are limited to entities in recent user history, which offers low coverage of future requests. Further, maintaining individual indices for millions of users is memory intensive and difficult to scale. In this work, we propose a personalized entity retrieval system that is robust to phonetic noise and ambiguity but is not limited to a personalized index. We achieve this by embedding user listening preferences into a contextual query embedding used in retrieval. We demonstrate our model’s ability to correct multiple error modes and show 91% improvement over baseline on the entity retrieval task. Finally, we optimize the end-to-end approach to fit within online latency constraints while maintaining gains in performance.

2022

pdf
Iterative Stratified Testing and Measurement for Automated Model Updates
Elizabeth Dekeyser | Nicholas Comment | Shermin Pei | Rajat Kumar | Shruti Rai | Fengtao Wu | Lisa Haverty | Kanna Shimizu
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: Industry Track

Automating updates to machine learning systems is an important but understudied challenge in AutoML. The high model variance of many cutting-edge deep learning architectures means that retraining a model provides no guarantee of accurate inference on all sample types. To address this concern, we present Automated Data-Shape Stratified Model Updates (ADSMU), a novel framework that relies on iterative model building coupled with data-shape stratified model testing and improvement. Using ADSMU, we observed a 26% (relative) improvement in accuracy for new model use cases on a large-scale NLU system, compared to a naive (manually) retrained baseline and current cutting-edge methods.