A comprehensive study of on-device NLP applications -- VQA, automated Form filling, Smart Replies for Linguistic Codeswitching
Not on the map. Why?
Abstract (arXiv)
Recent improvement in large language models, open doors for certain new experiences for on-device applications which were not possible before. In this work, we propose 3 such new experiences in 2 categories. First we discuss experiences which can be powered in screen understanding i.e. understanding whats on user screen namely - (1) visual question answering, and (2) automated form filling based on previous screen. The second category of experience which can be extended are smart replies to support for multilingual speakers with code-switching. Code-switching occurs when a speaker alternates between two or more languages. To the best of our knowledge, this is first such work to propose these tasks and solutions to each of them, to bridge the gap between latest research and real world impact of the research in on-device applications.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 8 of its 11 references that are in the map. First posted on arXiv 23 Sep 2024.
Builds on
8 of 11 references.
References · 8
- 2020DocVQA: A Dataset for VQA on Document Imagescited by 1,288
- 2018Personalizing Dialogue Agents: I have a dog, do you have pets too?cited by 820
- 2019LayoutLM: Pre-training of Text and Layout for Document Image Understandingcited by 549
- 2022LayoutLMv3: Pre-training for Document AI with Unified Text and Image Maskingcited by 481
- 2017Efficient Natural Language Response Suggestion for Smart Replycited by 228
- 2016Smart Reply: Automated Response Suggestion for Emailcited by 54
- 2022GODEL: Large-Scale Pre-Training for Goal-Directed Dialogcited by 50
- 2021MarkupLM: Pre-training of Text and Markup Language for Visually-rich Document Understandingcited by 44
Built on by
Not cited yet.