A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2016; you can also visit the original URL.
The file type is
Experimental results show the proposed approach is better than classical method in microblog real-time filtering with the usage of external knowledge base. ... This paper describes our efforts for TREC 2015 Microblog track. We applied the classic retrieval model combined with the external knowledge base, i.e., Wikipedia, for query expansion. ... CONCLUSION In this paper, we present our systems for TREC 2015 Microblog track Real-Time Filtering Task. ...dblp:conf/trec/LiuY15 fatcat:ubkqm4asdjhlfa7xewbyviw3oi
The task this year directly evolved from the real-time filtering task in the TREC 2015 Microblog Track  . ... EVALUATION DESIGN General Setup The design of the TREC 2016 Real-Time Summarization Track largely follows the design of the real-time filtering task in the TREC 2015 Microblog Track  . ...dblp:conf/trec/LinRTMV016 fatcat:akzydktxu5hynkur4755rimp6e
This is the final year of the Temporal Summarization track. For 2016, the track will merge with the Microblog track to become the new Real-Time Summarization (RTS) Track. ... Use a pre-filtered version of the TREC KBA 2014 Stream Corpus, denoted TREC-TS-2015F, which only contains documents from the 2015 event topic time periods. ...dblp:conf/trec/AslamDEMPS15 fatcat:ljksoyzqwvfwhi6eeuv4tjh77q
This paper describes our participation in the mobile notification and email digest tasks in the TREC 2015 Mircoblog track. ... Interest profiles contain the description of a topic that the user is interested in receiving relevant posts in real-time. ... The TREC 2015 Microblog track presents two scenarios for the real-time retrieval task: mobile notification (Scenario A) and email digest (Scenario B). ...dblp:conf/trec/DangMMIKM15 fatcat:6wzbgsljnvgyhl2pv25rveqw6m
Hence, there is a need for automatic approaches that summarize that content for the user in real-time. ... Through experimentation over the TREC TS 2013, 2014 and 2015 datasets, we show that explicit diversification for temporal summarization significantly outperforms classical noveltybased diversification, ... The track used the TREC Knowledge-Based Acceleration (KBA) stream corpus to represent the documents being published over time, for each year respectively. ...doi:10.1145/3158671 fatcat:fw4hyf2j5fccpldlgpfzq4bnra