CSIRO at 2017 TREC Precision Medicine Track

Vincent Nguyen; Sarvnaz Karimi; Sara Falamaki; Diego Molla; Cecile Paris; Stephen Wan

CSIRO at 2017 TREC Precision Medicine Track

Vincent Nguyen, Sarvnaz Karimi, Sara Falamaki, Diego Molla, Cecile Paris, Stephen Wan

School of Computing

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding contribution › peer-review

Abstract

We report on our participation as the CSIROmed team in the TREC 2017 Precision Medicine track. We submitted five runs for the scientific abstracts collection (MEDLINE and Cancer Proceedings), and five runs for the clinical trials collection. We experimented with a number of query expansion and search result re-ranking techniques. We used citation and MeSH-based re-ranking methods, as well as re-ranking based on a merging algorithm proposed for federated search. Our results show that boosting the gene variant in the query increases the relevance of the retrieved results. One of our five runs for clinical trials task was ranked in top
10 runs out of 133 runs submitted for this task.

Original language	English
Title of host publication	The Twenty-Sixth Text REtrieval Conference (TREC 2017) Proceedings
Publisher	National Institute of Standards and Technology
Number of pages	5
Publication status	Published - 2017
Event	26th Text REtrieval Conference (TREC 2017) - Gaithersburg, United States Duration: 15 Nov 2017 → 17 Nov 2017

Conference

Conference	26th Text REtrieval Conference (TREC 2017)
Country/Territory	United States
City	Gaithersburg
Period	15/11/17 → 17/11/17

Access to Document

https://trec.nist.gov/pubs/trec26/papers/CSIRO-PM.pdf

Cite this

@inproceedings{8fc7f6e0c0044763b706c5eaaaca0011,

title = "CSIRO at 2017 TREC Precision Medicine Track",

abstract = "We report on our participation as the CSIROmed team in the TREC 2017 Precision Medicine track. We submitted five runs for the scientific abstracts collection (MEDLINE and Cancer Proceedings), and five runs for the clinical trials collection. We experimented with a number of query expansion and search result re-ranking techniques. We used citation and MeSH-based re-ranking methods, as well as re-ranking based on a merging algorithm proposed for federated search. Our results show that boosting the gene variant in the query increases the relevance of the retrieved results. One of our five runs for clinical trials task was ranked in top10 runs out of 133 runs submitted for this task.",

author = "Vincent Nguyen and Sarvnaz Karimi and Sara Falamaki and Diego Molla and Cecile Paris and Stephen Wan",

year = "2017",

language = "English",

booktitle = "The Twenty-Sixth Text REtrieval Conference (TREC 2017) Proceedings",

publisher = "National Institute of Standards and Technology",

address = "United States",

note = "26th Text REtrieval Conference (TREC 2017) ; Conference date: 15-11-2017 Through 17-11-2017",

}

Nguyen, V, Karimi, S, Falamaki, S, Molla, D, Paris, C & Wan, S 2017, CSIRO at 2017 TREC Precision Medicine Track. in The Twenty-Sixth Text REtrieval Conference (TREC 2017) Proceedings. National Institute of Standards and Technology, 26th Text REtrieval Conference (TREC 2017), Gaithersburg, Maryland, United States, 15/11/17. <https://trec.nist.gov/pubs/trec26/papers/CSIRO-PM.pdf>

TY - GEN

T1 - CSIRO at 2017 TREC Precision Medicine Track

AU - Nguyen, Vincent

AU - Karimi, Sarvnaz

AU - Falamaki, Sara

AU - Molla, Diego

AU - Paris, Cecile

AU - Wan, Stephen

PY - 2017

Y1 - 2017

N2 - We report on our participation as the CSIROmed team in the TREC 2017 Precision Medicine track. We submitted five runs for the scientific abstracts collection (MEDLINE and Cancer Proceedings), and five runs for the clinical trials collection. We experimented with a number of query expansion and search result re-ranking techniques. We used citation and MeSH-based re-ranking methods, as well as re-ranking based on a merging algorithm proposed for federated search. Our results show that boosting the gene variant in the query increases the relevance of the retrieved results. One of our five runs for clinical trials task was ranked in top10 runs out of 133 runs submitted for this task.

AB - We report on our participation as the CSIROmed team in the TREC 2017 Precision Medicine track. We submitted five runs for the scientific abstracts collection (MEDLINE and Cancer Proceedings), and five runs for the clinical trials collection. We experimented with a number of query expansion and search result re-ranking techniques. We used citation and MeSH-based re-ranking methods, as well as re-ranking based on a merging algorithm proposed for federated search. Our results show that boosting the gene variant in the query increases the relevance of the retrieved results. One of our five runs for clinical trials task was ranked in top10 runs out of 133 runs submitted for this task.

UR - https://trec.nist.gov/pubs/trec26/trec2017.html

M3 - Conference proceeding contribution

BT - The Twenty-Sixth Text REtrieval Conference (TREC 2017) Proceedings

PB - National Institute of Standards and Technology

T2 - 26th Text REtrieval Conference (TREC 2017)

Y2 - 15 November 2017 through 17 November 2017

ER -

CSIRO at 2017 TREC Precision Medicine Track

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this