Filters








16,575 Hits in 6.3 sec

Silent Day Detection in Real-Time Summarization Track

Kuang Lu, Peilin Yang, Hui Fang
2017 Text Retrieval Conference  
Therefore, in this year's Real-Time Summarization Track, we focus on detecting silent days.  ...  Track results suggest that our methods can effectively detect silent days, which subsequently results in promising performances for both scenarios.  ...  Conclusion In this year's Real-Time Summarization Track, we directly address the problem of silent day detection.  ... 
dblp:conf/trec/LuY017 fatcat:z3a77wodyfecxd3vrjwfu4lxom

Microblog Processing: A Study

Sandip Modha
2017 Forum for Information Retrieval Evaluation  
In this paper, Twitter posts called tweets are studied from retrieval and extractive summarization perspectives.  ...  Given a set of topics or interest profiles or information requirement, a Microblog summarization system is desinged which process Twitter sample status stream and generate day-wise, topic-wise tweet summary  ...  In 2016 track was merged with temporal summarization and renamed as Real time summarization track [2] .  ... 
dblp:conf/fire/Modha17 fatcat:xolemzgx2fdc3oggvkzqrvcdqe

DAIICT at TREC RTS 2016: Live Push Notification and Email Digest

Sandip Modha, Krati Agrawal, Deepali Verma, Prasenjit Majumder, Chintak Mandalia
2016 Text Retrieval Conference  
This paper describes the participation of Information Retrieval Lab(IRLAB) at DA-IICT Gandhinagar,India in Real-Time Summarization track TREC 2016. This year TREC RTS offered two tasks.  ...  For the same, we have expanded interest profile using Word2vec training model with past 30 days tweets.  ...  Due to its real-time nature,this year TREC 2016 has offered Real-Time Summarization (RTS) track with following objectives: (i) how fast the participating system can deliver relevant and novel tweets based  ... 
dblp:conf/trec/ModhaAVMM16 fatcat:ktvh3glb5zbvllvp3gbeh4ki7e

PKUICST at TREC 2017 Real-Time Summarization Track: Push Notifications and Email Digest

Jizhi Tang, Chao Lv, Lili Yao, Dongyan Zhao
2017 Text Retrieval Conference  
In this paper, we describe our approaches and corresponding results in the Real-Time Summarization(RTS) track at the 2017 Text Retrieval Conference(TREC).  ...  Especially, in scenario A, the push notification scenario, we designed a decoupled system that can maintain high availability in order to meet the real-time requirements.  ...  Acknowledgments The work reported in this paper is supported by the National Natural Science Foundation of China Grant 61370116.  ... 
dblp:conf/trec/TangLYZ17 fatcat:x565fygblbdvnfnzvlzsnzn7xm

NOVASearch at TREC 2017 Real-Time Summarization Track

Gustavo Gonçalves, Flávio Martins, João Magalhães
2017 Text Retrieval Conference  
TREC 2017 Real-Time Summarization (RTS) provides a testbed for the development of stream based real-time summarization systems.  ...  The real-time push notifications scenario, or Scenario A, focuses on the identification and delivery of relevant information in near real-time.  ...  The TREC Real-Time Summarization (RTS) Track aims to tackle these issues through the delivery of the most relevant tweets in a near real-time push notifications scenario (A), or in a delayed digest in  ... 
dblp:conf/trec/GoncalvesMM17 fatcat:dywedw2pf5fgvjguhmkbyypzmq

Light-weight, Conservative, yet Effective: Scalable Real-time Tweet Summarization

Reem Suwaileh, Maram Hasanain, Tamer Elsayed
2016 Text Retrieval Conference  
In this paper, we tackle the problem of summarizing a stream of tweets given a pre-defined set of topics in the context of Qatar University's participation in TREC-2016 Real-Time Summarization (RTS) track  ...  At the end of each day, a list of potentially relevant tweets is retrieved using a query of topic title terms that is issued against an index of all streamed tweets of that day.  ...  In this paper, we present our real-time summarization system as a participant in TREC-2016 Real-time Summarization Track.  ... 
dblp:conf/trec/SuwailehHE16 fatcat:haehnlnno5f2rf2nbuxnkmjruq

Everything You Always Wanted to Know About TREC RTS* (*But Were Afraid to Ask) [article]

Gilles Hubert, Jose G. Moreno, Karen Pinel-Sauvagnat, Yoann Pitarch
2017 arXiv   pre-print
The TREC Real-Time Summarization (RTS) track provides a framework for evaluating systems monitoring the Twitter stream and pushing tweets to users according to given profiles.  ...  In this work, we perform a thorough analysis of each component of the framework used in 2016 and 2017 and found some limitations for the Scenario A of this track.  ...  The TREC campaign took an interest in the evaluation of such systems through various tracks and notably the ongoing Real-Time Summarization (RTS) track.  ... 
arXiv:1712.04671v1 fatcat:wyoh6spsczfyth3m7cpps7jn4i

EveTAR: Building a Large-Scale Multi-Task Test Collection over Arabic Tweets [article]

Maram Hasanain, Reem Suwaileh, Tamer Elsayed, Mucahid Kutlu, Hind Almerekhi
2017 arXiv   pre-print
That inherently facilitates the support of multiple tasks that generally revolve around events, namely event detection, ad-hoc search, timeline generation, and real-time summarization.  ...  We demonstrate the usability of EveTAR by evaluating existing algorithms in the respective tasks.  ...  We would like to thank the crowd workers and in-house annotators for their valuable efforts in producing high-quality judgments of tweets.  ... 
arXiv:1708.05517v2 fatcat:bl75l7fx6bgh5gyqjge35upjgi

Query Performance Prediction and Topic Shift in Microblog Retrieval

Kuang Lu, Hui Fang
2016 Text Retrieval Conference  
Therefore, in this year's Real-Time Summarization Track, we focus on estimating result cut-off thresholds and redundancy thresholds.  ...  In addition, since relevant but redundant tweets will be deemed as irrelevant, it is also important to detect whether a tweet contain novel information or not.  ...  The performances of submitted runs for different tasks are shown in Table 1 . Note that only primary metrics, which are EG − 1 for task A, and nDCG@10 − 1 are reported.  ... 
dblp:conf/trec/LuF16 fatcat:o73spzitjbhllixxlhyeplfpza

Overview of the TREC 2016 Real-Time Summarization Track

Jimmy Lin, Adam Roegiest, Luchen Tan, Richard McCreadie, Ellen M. Voorhees, Fernando Diaz
2016 Text Retrieval Conference  
ACKNOWLEDGMENTS This work was supported in part by the Natural Sciences and Engineering Research Council (NSERC) of Canada. Additional support came from the U.S.  ...  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 [6] .  ...  CONCLUSIONS The TREC 2016 Real-Time Summarization Track had several innovative elements.  ... 
dblp:conf/trec/LinRTMV016 fatcat:akzydktxu5hynkur4755rimp6e

Some thoughts from IRIT about the scenario A of the TREC RTS 2016 and 2017 tracks

Gilles Hubert, Jose G. Moreno, Karen Pinel-Sauvagnat, Yoann Pitarch
2017 Text Retrieval Conference  
The TREC Real-Time Summarization (RTS) track provides a framework for evaluating systems monitoring the Twitter stream and pushing tweets to users according to given profiles.  ...  In this work, we perform a thorough analysis of each component of the framework used for batch evaluation of scenario A in 2016 and 2017.  ...  The TREC campaign took an interest in the evaluation of such systems through various tracks and notably the ongoing Real-Time Summarization (RTS) track.  ... 
dblp:conf/trec/HubertMPP17 fatcat:vnwuu3p4czh33ne3y2tcrguepm

Assorted Textual Features and Dynamic Push Strategies for Real-time Tweet Notification

Kathy Lee, Ashequl Qadir, Vivek V. Datla, Sadid A. Hasan, Joey Liu, Aaditya Prakash, Oladimeji Farri
2016 Text Retrieval Conference  
In this paper, we describe our systems and corresponding results submitted to the Real-Time Summarization (RTS) track at the 2016 Text Retrieval Conference (TREC).  ...  In Scenario A of the task, tweets relevant to an interest profile were pushed to a live user in real-time. In Scenario B, a daily digest of relevant tweets was sent to a user.  ...  We address all of these challenges in our submitted runs for the Real-Time Summarization (RTS) track at the 2016 Text Retrieval Conference (TREC).  ... 
dblp:conf/trec/LeeQDHLPF16 fatcat:rpezqftc5zd3xpuhbwtga7gmw4

Overview of the TREC 2017 Real-Time Summarization Track

Jimmy Lin, Salman Mohammed, Royal Sequiera, Luchen Tan, Nimesh Ghelani, Mustafa Abualsaud, Richard McCreadie, Dmitrijs Milajevs, Ellen M. Voorhees
2017 Text Retrieval Conference  
We'd like to thank all the mobile assessors who participated in our user study and the NIST assessors.  ...  ACKNOWLEDGMENTS is work was supported in part by the Natural Sciences and Engineering Research Council (NSERC) of Canada.  ...  EVALUATION DESIGN 2.1 General Setup e overall design of the TREC 2017 Real-Time Summarization Track followed the iteration of the track in TREC 2016 [8] , which was itself adapted from the real-time ltering  ... 
dblp:conf/trec/LinMSTGAMMV17 fatcat:iagtggaonvai5hc7v3tgrccqe4

Burst Detection in Social Media Streams for Tracking Interest Profiles in Real Time

Cody Buntain, Jimmy Lin
2016 Proceedings of the 39th International ACM SIGIR conference on Research and Development in Information Retrieval - SIGIR '16  
While not as relatively performant in the Microblog Track's real-time notification task, RTTBurst did perform well (ranking 4th overall and second in the automatic category of Scenario B) in providing  ...  We laid out RTTBurst's architecture, our participation in and performance at the TREC 2015 Microblog Track, and a post hoc analysis for increasing RT-TBurst's performance.  ...  This paper describes RTTBurst 1 , one of the systems participating in TREC's 2015 microblog track, and its use of linear regression to detect bursts in Twitter's social media stream in real time.  ... 
doi:10.1145/2911451.2914733 dblp:conf/sigir/BuntainL16 fatcat:aw7cesqksbhm7d2ekj7bsxgzaa

CCNU at TREC 2016 Real-Time Summarization Track

Chao Bei, Po Hu
2016 Text Retrieval Conference  
This paper describes our approach to real-time summarization track for push notification scenario and email digest scenario in TREC 2016.  ...  In the email digest scenario, in addition to considering these factors, we additionally adopted a novel TF-IDF strategy to automatically rank tweets at the end of a day.  ...  Conclusion In this paper, we present our system for real-time summarization track in TREC 2016. For the scenario A, we expand query via Bing Search API.  ... 
dblp:conf/trec/BeiH16 fatcat:5kb6un23lfgnlpu3zwiw3cb5oi
« Previous Showing results 1 — 15 out of 16,575 results