Details
| Original language | English |
|---|---|
| Title of host publication | WWW 2015 Companion - Proceedings of the 24th International Conference on World Wide Web |
| Pages | 247-250 |
| Number of pages | 4 |
| ISBN (electronic) | 9781450334730 |
| Publication status | Published - 18 May 2015 |
| Event | 24th International Conference on World Wide Web, WWW 2015 - Florence, Italy Duration: 18 May 2015 → 22 May 2015 |
Publication series
| Name | WWW 2015 Companion - Proceedings of the 24th International Conference on World Wide Web |
|---|
Abstract
Fully understanding an older news article requires context knowledge from the time of article creation. Finding infor- mation about such context is a tedious and time-consuming task, which distracts the reader. Simple contextualization via Wiki cation is not su cient here. The retrieved con- text information has to be time-aware, concise (not full Wiki pages) and focused on the coherence of the article topic. In this paper, we present Contextualizer, a web-based system that acquires additional information for supporting inter- pretations of a news article of interest that requires a map- ping, in this case, a kind of time-travel translation between present context knowledge and context knowledge at time of text creation. For a given article, the system provides a GUI that allows users to highlight their interested key- words which are then used to construct appropriate queries for retrieving contextualization candidates. Contextualizer exploits different kinds of information such as temporal simi- larity and textual complementarity to re-rank the candidates and presents to users in a friendly and interactive web-based interface.
Keywords
- Complementarity, Temporal context, Time-aware contextualization
ASJC Scopus subject areas
- Computer Science(all)
- Computer Networks and Communications
- Computer Science(all)
- Software
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
WWW 2015 Companion - Proceedings of the 24th International Conference on World Wide Web. 2015. p. 247-250 (WWW 2015 Companion - Proceedings of the 24th International Conference on World Wide Web).
Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review
}
TY - GEN
T1 - Time-travel translator
T2 - 24th International Conference on World Wide Web, WWW 2015
AU - Tran, Nam Khanh
AU - Ceroni, Andrea
AU - Kanhabua, Nattiya
AU - Niederée, Claudia
N1 - The work was partially funded by the European Commission for the FP7 project ForgetIT under grant No. 600826 and the German Federal Ministry of Education and Research (BMBF) for the project “Gute Arbeit” nach dem Boom (Re-SozIT) (01UG1249C)
PY - 2015/5/18
Y1 - 2015/5/18
N2 - Fully understanding an older news article requires context knowledge from the time of article creation. Finding infor- mation about such context is a tedious and time-consuming task, which distracts the reader. Simple contextualization via Wiki cation is not su cient here. The retrieved con- text information has to be time-aware, concise (not full Wiki pages) and focused on the coherence of the article topic. In this paper, we present Contextualizer, a web-based system that acquires additional information for supporting inter- pretations of a news article of interest that requires a map- ping, in this case, a kind of time-travel translation between present context knowledge and context knowledge at time of text creation. For a given article, the system provides a GUI that allows users to highlight their interested key- words which are then used to construct appropriate queries for retrieving contextualization candidates. Contextualizer exploits different kinds of information such as temporal simi- larity and textual complementarity to re-rank the candidates and presents to users in a friendly and interactive web-based interface.
AB - Fully understanding an older news article requires context knowledge from the time of article creation. Finding infor- mation about such context is a tedious and time-consuming task, which distracts the reader. Simple contextualization via Wiki cation is not su cient here. The retrieved con- text information has to be time-aware, concise (not full Wiki pages) and focused on the coherence of the article topic. In this paper, we present Contextualizer, a web-based system that acquires additional information for supporting inter- pretations of a news article of interest that requires a map- ping, in this case, a kind of time-travel translation between present context knowledge and context knowledge at time of text creation. For a given article, the system provides a GUI that allows users to highlight their interested key- words which are then used to construct appropriate queries for retrieving contextualization candidates. Contextualizer exploits different kinds of information such as temporal simi- larity and textual complementarity to re-rank the candidates and presents to users in a friendly and interactive web-based interface.
KW - Complementarity
KW - Temporal context
KW - Time-aware contextualization
UR - http://www.scopus.com/inward/record.url?scp=84968610559&partnerID=8YFLogxK
U2 - 10.1145/2740908.2742841
DO - 10.1145/2740908.2742841
M3 - Conference contribution
AN - SCOPUS:84968610559
T3 - WWW 2015 Companion - Proceedings of the 24th International Conference on World Wide Web
SP - 247
EP - 250
BT - WWW 2015 Companion - Proceedings of the 24th International Conference on World Wide Web
Y2 - 18 May 2015 through 22 May 2015
ER -