A comprehensive study of on-device NLP applications -- VQA, automated Form filling, Smart Replies for Linguistic Codeswitching
Fuente:
arXiv
Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916413571072000 |
|---|---|
| author | Goyal, Naman |
| author_facet | Goyal, Naman |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_19010 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | A comprehensive study of on-device NLP applications -- VQA, automated Form filling, Smart Replies for Linguistic Codeswitching Goyal, Naman Computation and Language Artificial Intelligence Machine Learning 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. |
| title | A comprehensive study of on-device NLP applications -- VQA, automated Form filling, Smart Replies for Linguistic Codeswitching |
| topic | Computation and Language Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2409.19010 |