Overview of the TREC 2011 Microblog Track

By Iadh Ounis, Craig Macdonald, Jimmy J. Lin, Ian Soboroff. 2011

246 citations recorded by the source corpus.

Subfields: Information Retrieval & Search

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Information Retrieval & Search

Citations in the corpus

Pretrained Transformers for Text Ranking: BERT and Beyond (2020, background): “m above by simply avoiding it. An earlier work [Yang et al., 2019e] that eventually gave rise to Birch ﬁrst examined the task of ranking tweets, using test collections from the TREC Microblog Tracks [Ounis et al., 2011, Soboroff et al., 2012, Lin and Efron, 2013, Lin et al., 2014]. These evaluations”
Simple Applications of BERT for Ad Hoc Document Retrieval (2019, neutral): “Experimental results are shown in Table 1, where we present average precision (AP) and precision at rank 30 (P30), the two ofﬁcial metrics of the evaluation (Ounis et al., 2011).”
Cross-Domain Sentence Modeling for Relevance Transfer with BERT (2019, methodology): “We fine-tune BERT on three such sentenceand passage-level datasets individually and in combination: TREC Microblog [47], MicroSoft MAchine Reading Comprehension [6] and TREC Complex Answer Retrieval [20].”
On building a reusable Twitter corpus (2012, unknown): “that investigated tweet search and ranking [2].”
Overview of the TREC-2014 Microblog Track (2014, methodology): “We refer the reader to previous track overview papers [8, 12, 9] for details on the setup of the ad hoc task.”
The Impact of Score Ties on Repeatability in Document Ranking (2018, result): “The organizers of the TREC Microblog Tracks [8] have discovered that tie-breaking heuristics can have a large impact on effectiveness, since tweets are short and hence many retrieved results share the same score.”
Overview of the TREC-2012 Microblog Track (2014, methodology): “However, as reported in last year’s track overview paper [3], this created signiﬁcant ambiguity regarding how to interpret participants’ retrieval scores and ranks.”
Overview of the TREC-2013 Microblog Track (2013, methodology): “Here, we provide a quick recap, but refer the reader to previous track overview papers for more details [1, 2].”
Applying BERT to Document Retrieval with Birch (2019, background): “Experimental results are shown in Table 1, where we present average precision (AP) and precision at rank 30 (P@30), the two ofﬁcial metrics of the evaluation (Ounis et al., 2011).”
Everyone's Invited: A New Paradigm for Evaluation on Non-Transferable Datasets (2015, background): “While social media data has still been used for evaluation tasks within the research community (Ounis et al. 2011; Nakov et al. 2013), research efforts have been hindered by both problems, with the resulting datasets size-constrained by the limited ability to reconstruct the original data and with…”
Learning to Rank Short Text Pairs with Convolutional Deep Neural Networks (2015, methodology): “Following [4, 23], we regard minimally and highly relevant documents as relevant and use the TMB2012 evaluation script.”
TREC-COVID: rationale and structure of an information retrieval shared task for COVID-19 (2020, background): “For perspective, only one task in the 28-year history of TREC (including 193 separate tasks) had more participants [17], and TREC-COVID had a submission deadline less than one month after it was unofficially announced and one week after it was officially announced.”
Modelling input texts: from Tree Kernels to Deep Learning (2015, methodology): “We focus on the 2011 and 2012 editions of the ad-hoc retrieval task at TREC microblog tracks [103, 149].”