FPI: Failure Point Isolation in Large-scale Conversational Assistants

Rinat Khaziev, Usman Shahid, Tobias Röding, Rakesh Chada, Emir Kapanci, Pradeep Natarajan


Abstract
Large-scale conversational assistants such as Cortana, Alexa, Google Assistant and Siri process requests through a series of modules for wake word detection, speech recognition, language understanding and response generation. An error in one of these modules can cascade through the system. Given the large traffic volumes in these assistants, it is infeasible to manually analyze the data, identify requests with processing errors and isolate the source of error. We present a machine learning system to address this challenge. First, we embed the incoming request and context, such as system response and subsequent turns, using pre-trained transformer models. Then, we combine these embeddings with encodings of additional metadata features (such as confidence scores from different modules in the online system) using a “mixing-encoder” to output the failure point predictions. Our system obtains 92.2% of human performance on this task while scaling to analyze the entire traffic in 8 different languages of a large-scale conversational assistant. We present detailed ablation studies analyzing the impact of different modeling choices.
Anthology ID:
2022.naacl-industry.17
Volume:
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Industry Track
Month:
July
Year:
2022
Address:
Hybrid: Seattle, Washington + Online
Editors:
Anastassia Loukina, Rashmi Gangadharaiah, Bonan Min
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
141–148
Language:
URL:
https://aclanthology.org/2022.naacl-industry.17
DOI:
10.18653/v1/2022.naacl-industry.17
Bibkey:
Cite (ACL):
Rinat Khaziev, Usman Shahid, Tobias Röding, Rakesh Chada, Emir Kapanci, and Pradeep Natarajan. 2022. FPI: Failure Point Isolation in Large-scale Conversational Assistants. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Industry Track, pages 141–148, Hybrid: Seattle, Washington + Online. Association for Computational Linguistics.
Cite (Informal):
FPI: Failure Point Isolation in Large-scale Conversational Assistants (Khaziev et al., NAACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.naacl-industry.17.pdf
Video:
 https://aclanthology.org/2022.naacl-industry.17.mp4