AD3: Attentive Deep Document Dater

Swayambhu Nath Ray, Shib Sankar Dasgupta, Partha Talukdar


Abstract
Knowledge of the creation date of documents facilitates several tasks such as summarization, event extraction, temporally focused information extraction etc. Unfortunately, for most of the documents on the Web, the time-stamp metadata is either missing or can’t be trusted. Thus, predicting creation time from document content itself is an important task. In this paper, we propose Attentive Deep Document Dater (AD3), an attention-based neural document dating system which utilizes both context and temporal information in documents in a flexible and principled manner. We perform extensive experimentation on multiple real-world datasets to demonstrate the effectiveness of AD3 over neural and non-neural baselines.
Anthology ID:
D18-1213
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:
1871–1880
Language:
URL:
https://aclanthology.org/D18-1213
DOI:
10.18653/v1/D18-1213
Bibkey:
Cite (ACL):
Swayambhu Nath Ray, Shib Sankar Dasgupta, and Partha Talukdar. 2018. AD3: Attentive Deep Document Dater. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 1871–1880, Brussels, Belgium. Association for Computational Linguistics.
Cite (Informal):
AD3: Attentive Deep Document Dater (Ray et al., EMNLP 2018)
Copy Citation:
PDF:
https://aclanthology.org/D18-1213.pdf
Video:
 https://aclanthology.org/D18-1213.mp4
Code
 malllabiisc/AD3