Overview of the TREC-2014 Microblog Track

By Jimmy J. Lin, Yulu Wang, Miles Efron, Garrick Sherman. 2014

116 citations recorded by the source corpus.

Subfields: Evaluation & Benchmarks

How researchers see this paper

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

In Evaluation & Benchmarks

1. Jimmy J. Lin
2. Nick Craswell
3. Rodrigo Nogueira
4. Bhaskar Mitra
5. Emine Yilmaz
6. Zeynep Akkalyoncu Yilmaz
7. Andrew Yates
8. Daniel Fernando Campos

Citations in the corpus

• Pretrained Transformers for Text Ranking: BERT and Beyond (2020, background): “9e] 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 focused on information seeking in a microblogging context, wher”
• Simple Applications of BERT for Ad Hoc Document Retrieval (2019, background): “Test collections from the TREC Microblog Tracks were used for fine-tuning the BERT model, using cross-entropy loss.”
• MS MARCO: Benchmarking Ranking Models in the Large-Data Regime (2021, methodology): “Yilmaz et al. [85] finetune a BERT-based [21] model on MS MARCO, TREC CAR [22] and TREC Microblog [43] datasets and evaluate them on three TREC newswire collections: Robust04 [74], Core17 [1], and Core18.”
• Cross-Domain Modeling of Sentence-Level Evidence for Document Retrieval (2019, unknown): “…of test collections that fortuitously contain passage-level relevance evidence: the MA-chine Reading COmprehension (MS MARCO) dataset (Bajaj et al., 2018), the TREC Complex Answer Retrieval (CAR) dataset (Dietz et al., 2017), and the TREC Microblog (MB) datasets (Lin et al., 2014), described below.”
• Applying BERT to Document Retrieval with Birch (2019, methodology): “(2019c), Birch was evaluated on tweet test collections from the TREC Microblog Tracks, 2011 to 2014 (Lin et al., 2014).”
• Overview of the TREC 2016 Real-Time Summarization Track (2016, methodology): “We adopted the Tweet Timeline Generation (TTG) evaluation methodology that was originally developed for the TREC 2014 Microblog Track [5] and also used in the TREC 2015 Microblog Track [6].”
• Assessor Differences and User Preferences in Tweet Timeline Generation (2015, background): “The two assessors at UMD were graduate students in computer science (both male).”
• Cross-Lingual Training of Neural Models for Document Ranking (2020, methodology): “Following Akka-lyoncu Yilmaz et al. (2019), BERT is fine-tuned with data from the TREC Microblog Tracks (Lin et al., 2014) (MB for short).”
• Cross-Lingual Relevance Transfer for Document Retrieval (2019, methodology): “We used data from the Microblog Tracks from TREC 2011–2014 (Lin et al., 2014), setting aside 75% of the total data for training and the rest for validation, which is used for selecting the best model parameters.”