TREC 2007 Genomics Track Overview

By William R. Hersh, Aaron M. Cohen, Jianji Yang, Ravi Teja Bhupatiraju, Phoebe M. Roberts, Marti A. Hearst. 2007

468 citations recorded by the source corpus.

Subfields: Natural Language Processing, 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 Natural Language Processing

In Evaluation & Benchmarks

Citations in the corpus

Pretrained Transformers for Text Ranking: BERT and Beyond (2020, methodology): “TREC tracks have been organized in this domain as well: the Genomics Track, which ran from 2003 [Hersh and Bhupatiraju, 2003] to 2007 [Hersh et al., 2007], represented information needs closer to those of researchers.”
Constructing Datasets for Multi-hop Reading Comprehension Across Documents (2017, methodology): “Existing RC datasets are either severely limited in size (Hersh et al., 2007) or cover a very diverse set of query types (Nentidis et al., 2017), complicating the application of neural models that have seen successes for other domains (Wiese et al., 2017).”
PubMedQA: A Dataset for Biomedical Research Question Answering (2019, background): “In 2006 and 2007, TREC held QA challenges on genomics corpus (Hersh et al., 2006, 2007), where the task is to retrieve relevant documents for 36 and 38 topic questions, respectively.”
Literature mining for the biologist: from information retrieval to biological discovery (2006, background): “However, blind assessments ( Box 2 ) have shown that most of the lessons that have been learned from IR in other research fields carry over to the biomedical science”
Biomedical language processing: what's beyond PubMed? (2006, background): “Perhaps the most influential of these evaluations has been the TREC Genomics Track (Hersh and Bhupatiraju, 2003; Hersh et al., 2004, 2005 ).”
Overview of the protein-protein interaction annotation extraction task of BioCreative II (2008, methodology): “…curve (AUC) were used, as is customary for information retrieval experiments (see, for example, the TREC [Text Retrieval Conference] competitions [15], which have recently included a Genomics track): Where TP is number of true-positive predictions (interaction-relevant abstracts correctly…”
A shared task involving multi-label classification of clinical free text (2007, result): “Compared to other recent text classiﬁcation shared tasks in the biomedical domain (Uzuner et al., 2006; Hersh et al., 2004; Hersh et al., 2005), this task required categorization with respect to a set of labels more than an order of magnitude larger than previous evaluations.”
Frontiers of biomedical text mining: current progress (2007, background): “Genomics track task [80] was to extract passages”
Toward a semantic granularity model for domain-specific information retrieval (2011, background): “It should be noted that the best MAP achieved in the 2006 TREC Genomics Track was slightly higher than 0.5 [Hersh et al. 2006].”
Is searching full text more effective than searching abstracts? (2009, methodology): “Experiments reported in this article were conducted with the test collection from the TREC 2007 genomics track evaluation [26].”
Test Collection Based Evaluation of Information Retrieval Systems (2010, background): “• categorizing and/or retrieving streamed text, as addressed in the routing and filtering tracks [200]; • medical scholarly articles in the TREC-based genomics collection where matching to variants of gene names became a part of the search task [119]; • search across languages with English queries r”
Answering Clinical Questions with Knowledge-Based and Statistical Techniques (2007, background): “Recent results from TREC have demonstrated that high performance ad hoc retrieval is possible in the genomics domain (Hersh et al. 2005), and it is not a stretch to imagine adopting these technologies for clinical tasks.”
Overview of BioCreAtIvE: critical assessment of information extraction for biology (2005, methodology): “The second related evaluation is the recently introduced Genomics track [28] of annual Text Retrieval Conferences (TREC) [29].”