Exploratory Navigation and Selective Reading

Abstract

Navigating a collection of documents can be facilitated by obtaining a human-understandable concept hierarchy with links to the content. This is a non-trivial task for two reasons. First, defining concepts that are understandable by an average consumer and yet meaningful for a large variety of corpora is hard. Second, creating semantically meaningful yet intuitive hierarchical representation is hard, and can be task dependent. We present out system Navigation.ai which automatically processes a document collection, induces a concept hierarchy using Wikipedia and presents an interactive interface that helps user navigate to individual paragraphs using concepts.

Cite

Text

Modani et al. "Exploratory Navigation and Selective Reading." AAAI Conference on Artificial Intelligence, 2020. doi:10.1609/AAAI.V34I09.7103

Markdown

[Modani et al. "Exploratory Navigation and Selective Reading." AAAI Conference on Artificial Intelligence, 2020.](https://mlanthology.org/aaai/2020/modani2020aaai-exploratory/) doi:10.1609/AAAI.V34I09.7103

BibTeX

@inproceedings{modani2020aaai-exploratory,
  title     = {{Exploratory Navigation and Selective Reading}},
  author    = {Modani, Natwar and Maheshwari, Paridhi and Deshpande, Harsh and Sirpurkar, Saurab and Diviya,  and Aditya, Somak},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2020},
  pages     = {13632-13633},
  doi       = {10.1609/AAAI.V34I09.7103},
  url       = {https://mlanthology.org/aaai/2020/modani2020aaai-exploratory/}
}