Ad3: Attentive deep document dater

Ray, SN and Dasgupta, SS and Talukdar, P (2018) Ad3: Attentive deep document dater. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, 31st October- 4th November 2018, Brussels, Belgium, pp. 1871-1880.

PDF EMP_NAT_LAN_PRO_EMN_1871-1880_2018.pdf - Published Version Restricted to Registered users only Download (902kB) | Request a copy

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. © 2018 Association for Computational Linguistics

Item Type:	Conference Paper
Publication:	Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018
Publisher:	Association for Computational Linguistics
Additional Information:	cited By 0; Conference of 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018 ; Conference Date: 31 October 2018 Through 4 November 2018; Conference Code:158085
Keywords:	Information analysis, Document contents; Event extraction; Real-world datasets; Temporal information; Time stamps, Natural language processing systems
Department/Centre:	Division of Interdisciplinary Sciences > Computational and Data Sciences
Date Deposited:	03 Sep 2020 06:30
Last Modified:	03 Sep 2020 06:30
URI:	http://eprints.iisc.ac.in/id/eprint/64978

Actions (login required)

View Item