Fully understanding an older news article requires context knowledge from the time of article creation. Finding information about such context is a tedious and time-consuming task, which distracts the reader. Simple contextualization via Wikication is not sufficient here. The retrieved context information has to be time-aware, concise (not full Wikipages) and focused on the coherence of the article topic.
In this paper, we present an approach for time-aware re-contextualization, which takes those requirements into account in order to improve reading experience. For this purpose, we propose (1) different query formulation methods for retrieving contextualization candidates and (2) ranking methods taking into account topical and temporal relevance as well as complementarity with respect to the original text.
We evaluate our proposed approaches through extensive experiments using real-world datasets and ground-truth consisting of approximately 9,500 article/context pairs. To this end, our experimental results show that our methods retrieve contextualization information for older articles from the New York Times Archive with high precision and outperform baselines significantly.
%0 Conference Paper
%1 tran2015supporting
%A Tran, Nam Khanh
%A Ceroni, Andrea
%A Kanhabua, Nattiya
%A Niederée, Claudia
%B Proceedings of the Eighth International Conference on Web Search and Data Mining
%D 2015
%K forgetit myown
%T Back to the Past: Supporting Interpretations of Forgotten Stories by Time-aware Re-Contextualization
%X Fully understanding an older news article requires context knowledge from the time of article creation. Finding information about such context is a tedious and time-consuming task, which distracts the reader. Simple contextualization via Wikication is not sufficient here. The retrieved context information has to be time-aware, concise (not full Wikipages) and focused on the coherence of the article topic.
In this paper, we present an approach for time-aware re-contextualization, which takes those requirements into account in order to improve reading experience. For this purpose, we propose (1) different query formulation methods for retrieving contextualization candidates and (2) ranking methods taking into account topical and temporal relevance as well as complementarity with respect to the original text.
We evaluate our proposed approaches through extensive experiments using real-world datasets and ground-truth consisting of approximately 9,500 article/context pairs. To this end, our experimental results show that our methods retrieve contextualization information for older articles from the New York Times Archive with high precision and outperform baselines significantly.
@inproceedings{tran2015supporting,
abstract = {Fully understanding an older news article requires context knowledge from the time of article creation. Finding information about such context is a tedious and time-consuming task, which distracts the reader. Simple contextualization via Wikication is not sufficient here. The retrieved context information has to be time-aware, concise (not full Wikipages) and focused on the coherence of the article topic.
In this paper, we present an approach for time-aware re-contextualization, which takes those requirements into account in order to improve reading experience. For this purpose, we propose (1) different query formulation methods for retrieving contextualization candidates and (2) ranking methods taking into account topical and temporal relevance as well as complementarity with respect to the original text.
We evaluate our proposed approaches through extensive experiments using real-world datasets and ground-truth consisting of approximately 9,500 article/context pairs. To this end, our experimental results show that our methods retrieve contextualization information for older articles from the New York Times Archive with high precision and outperform baselines significantly.},
added-at = {2015-01-16T10:27:25.000+0100},
author = {Tran, Nam Khanh and Ceroni, Andrea and Kanhabua, Nattiya and Niederée, Claudia},
biburl = {https://www.bibsonomy.org/bibtex/2802e6af9a2736c36b63e1f3e14f22aee/xander71988},
booktitle = {Proceedings of the Eighth International Conference on Web Search and Data Mining},
interhash = {bee69c918882a30ed487f4f2db840611},
intrahash = {802e6af9a2736c36b63e1f3e14f22aee},
keywords = {forgetit myown},
series = {WSDM'2015},
timestamp = {2015-01-16T10:33:18.000+0100},
title = {Back to the Past: Supporting Interpretations of Forgotten Stories by Time-aware Re-Contextualization},
year = 2015
}