Adaptive Beam Search to Enhance On-device Abstractive Summarization
Harichandana B S S, Sumit Kumar

TL;DR
This paper introduces an adaptive beam search method for on-device abstractive summarization, enabling privacy-preserving, efficient summarization of SMS, voice messages, and documents with reduced model size and maintained quality.
Contribution
It proposes the first adaptive beam search technique for on-device summarization that adapts to multiple data sources and reduces model size via knowledge distillation.
Findings
Model size reduced by 30.9% using knowledge distillation.
Achieves 97.6% lesser memory footprint while maintaining or improving summarization quality.
First on-device summarization pipeline adaptable to multiple data sources.
Abstract
We receive several essential updates on our smartphones in the form of SMS, documents, voice messages, etc. that get buried beneath the clutter of content. We often do not realize the key information without going through the full content. SMS notifications sometimes help by giving an idea of what the message is about, however, they merely offer a preview of the beginning content. One way to solve this is to have a single efficient model that can adapt and summarize data from varied sources. In this paper, we tackle this issue and for the first time, propose a novel Adaptive Beam Search to improve the quality of on-device abstractive summarization that can be applied to SMS, voice messages and can be extended to documents. To the best of our knowledge, this is the first on-device abstractive summarization pipeline to be proposed that can adapt to multiple data sources addressing privacy…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
MethodsRefunds@Expedia|||How do I get a full refund from Expedia? · Attention Is All You Need · Linear Layer · Attention Dropout · Dropout · Layer Normalization · WordPiece · Weight Decay · Dense Connections · Multi-Head Attention
