DeepAI AI Chat
Log In Sign Up

AD3: Attentive Deep Document Dater

01/21/2019
by   Swayambhu Nath Ray, et al.
indian institute of science
0

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.

READ FULL TEXT
02/01/2019

Dating Documents using Graph Convolution Networks

Document date is essential for many important tasks, such as document re...
10/15/2021

Modeling Endorsement for Multi-Document Abstractive Summarization

A crucial difference between single- and multi-document summarization is...
10/03/2021

Multi-Document Keyphrase Extraction: A Literature Review and the First Dataset

Keyphrase extraction has been comprehensively researched within the sing...
06/23/2020

On the Programmatic Generation of Reproducible Documents

Reproducible document standards, like R Markdown, facilitate the program...
03/23/2018

WikiRank: Improving Keyphrase Extraction Based on Background Knowledge

Keyphrase is an efficient representation of the main idea of documents. ...
01/29/2022

Le Processus Powered Dirichlet-Hawkes comme A Priori Flexible pour Clustering Temporel de Textes

The textual content of a document and its publication date are intertwin...

Code Repositories

AD3

EMNLP 2018: AD3: Attentive Deep Document Dater :: Swayambhu Nath Ray, Shib Sankar Dasgupta, Partha Talukdar


view repo