On-Device Tag Generation for Unstructured Text

TL;DR

This paper introduces an efficient on-device system that generates meaningful tags from unstructured text using a CNN model and pruned ConceptNet, improving data organization and retrieval on mobile devices.

Contribution

It presents a novel pipeline combining a pruned ConceptNet and CNN for on-device tag generation from unstructured text, with a new ranking algorithm for top tag extraction.

Findings

Achieves efficient on-device tag generation with high relevance.

Enhances user experience by improving data categorization and search.

Utilizes a novel ranking algorithm for selecting top tags.

Abstract

With the overwhelming transition to smart phones, storing important information in the form of unstructured text has become habitual to users of mobile devices. From grocery lists to drafts of emails and important speeches, users store a lot of data in the form of unstructured text (for eg: in the Notes application) on their devices, leading to cluttering of data. This not only prevents users from efficient navigation in the applications but also precludes them from perceiving the relations that could be present across data in those applications. This paper proposes a novel pipeline to generate a set of tags using world knowledge based on the keywords and concepts present in unstructured textual data. These tags can then be used to summarize, categorize or search for the desired information thus enhancing user experience by allowing them to have a holistic outlook of the kind of information stored in the form of unstructured text. In the proposed system, we use an on-device (mobile phone) efficient CNN model with pruned ConceptNet resource to achieve our goal. The architecture also presents a novel ranking algorithm to extract the top n tags from any given text.