RMIT at TREC 2011 Microblog Track
نویسندگان
چکیده
This paper describes our submission to the TREC 2011 microblog task. For the experiments, we use our new self-index search engine, NeWT, to support ranked search in the Twitter document corpus. We use a combination of phrase queries and degrading conjunctive Boolean intersection to improve retrieval effectiveness. Keywords-self-index; full-text search, phrases, threshold; intersection
منابع مشابه
PKU_ICST at TREC 2011 Microblog Track
This paper describes the PKU_ICST participation in the TREC 2011 Microblog track. In the first year of Microblog track, we designed a group of experiments to verify whether external resources and future resources would improve the performance of our system. Moreover, given that microblog track is a real-‐‐time adhoc task, we explored an ap...
متن کاملUniversity of Lugano at TREC 2011 Microblog Track
In this document we present the participation of University of Lugano in the Microblog track of TREC 2011. We describe our approach based on a time-based filtering algorithm of retrieved documents. We highlight the results and the possible improvement of the described technique.
متن کاملRMIT at the Crowdsourcing Track of TREC 2011
In this paper we describe our submission to the crowdsourcing track of TREC 2011. We first describe our crowdsourcing environment. Next we evaluate our approach and discuss our results. We conclude with a discussion of problems encountered during our participation.
متن کاملDUTIR at TREC 2011 Microblog Track
In TREC 2011 Microblog Track, we explore the use of pseudo relevance feedback to expand original query terms in topics. Hyperlink is used to enhance the performance of the retrieval results. And we set a threshold of entropy to filter retrieval results. Microblog is a Realtime Adhoc Task, so we make use of average querytweettime that comes from pseudo relevance feedback to change retrieval scor...
متن کامل