Content Explorer: Recommending Novel Entities for a Document Writer

Michal Lukasik, Richard Zens


Abstract
Background research is an essential part of document writing. Search engines are great for retrieving information once we know what to look for. However, the bigger challenge is often identifying topics for further research. Automated tools could help significantly in this discovery process and increase the productivity of the writer. In this paper, we formulate the problem of recommending topics to a writer. We consider this as a supervised learning problem and run a user study to validate this approach. We propose an evaluation metric and perform an empirical comparison of state-of-the-art models for extreme multi-label classification on a large data set. We demonstrate how a simple modification of the cross-entropy loss function leads to improved results of the deep learning models.
Anthology ID:
D18-1374
Volume:
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
Month:
October-November
Year:
2018
Address:
Brussels, Belgium
Editors:
Ellen Riloff, David Chiang, Julia Hockenmaier, Jun’ichi Tsujii
Venue:
EMNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
3371–3380
Language:
URL:
https://aclanthology.org/D18-1374
DOI:
10.18653/v1/D18-1374
Bibkey:
Cite (ACL):
Michal Lukasik and Richard Zens. 2018. Content Explorer: Recommending Novel Entities for a Document Writer. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 3371–3380, Brussels, Belgium. Association for Computational Linguistics.
Cite (Informal):
Content Explorer: Recommending Novel Entities for a Document Writer (Lukasik & Zens, EMNLP 2018)
Copy Citation:
PDF:
https://aclanthology.org/D18-1374.pdf
Attachment:
 D18-1374.Attachment.tgz