@InProceedings{goodwin2017utd,
title = {UTD HLTRI at TREC 2017: Precision Medicine Track},
author = {Goodwin, Travis R. and Skinner, Michael A. and Harabagiu, Sanda M.},
booktitle = {Proceedings of the 26th Text REtrieval Conference},
shortbooktitle={TREC '17},
location= {Washington, DC, USA},
year = {2017},
month = {November},
url_Paper = {papers/trec_2017_draft.pdf},
url_Slides = {papers/trec_2017_slides.pdf},
  abstract={"In this paper, we describe the system designed for the TREC
2017 Precision Medicine track by the University of Texas
at Dallas (UTD) Human Language Technology Research In-
stitute (HLTRI). Our system incorporates an aspect-based
retrieval paradigm wherein each of the four structured com-
ponents of the topic is cast as a separate aspect, along with
two “hidden” aspects encoding the need that retrieved docu-
ments be within the domain of precision medicine and that
retrieved documents have a focus on treatment. To this end,
we construct knowledge graph encoding the relationships be-
tween drugs, genes, and mutations. Our experiments reveal
that the aspect-based approach leads to improved quality of
retrieved scientific articles and clinical trials."},
keywords = {precision medicine, knowledge graph, information retrieval, question answering, medical informatics}
}

{"_id":"e77cna8bScwDHfWri","bibbaseid":"goodwin-skinner-harabagiu-utdhltriattrec2017precisionmedicinetrack-2017","downloads":0,"creationDate":"2017-12-12T00:23:28.489Z","title":"UTD HLTRI at TREC 2017: Precision Medicine Track","author_short":["Goodwin, T. R.","Skinner, M. A.","Harabagiu, S. M."],"year":2017,"bibtype":"inproceedings","biburl":"http://www.hlt.utdallas.edu/~travis/publications.bib","bibdata":{"bibtype":"inproceedings","type":"inproceedings","title":"UTD HLTRI at TREC 2017: Precision Medicine Track","author":[{"propositions":[],"lastnames":["Goodwin"],"firstnames":["Travis","R."],"suffixes":[]},{"propositions":[],"lastnames":["Skinner"],"firstnames":["Michael","A."],"suffixes":[]},{"propositions":[],"lastnames":["Harabagiu"],"firstnames":["Sanda","M."],"suffixes":[]}],"booktitle":"Proceedings of the 26th Text REtrieval Conference","shortbooktitle":"TREC '17","location":"Washington, DC, USA","year":"2017","month":"November","url_paper":"papers/trec_2017_draft.pdf","url_slides":"papers/trec_2017_slides.pdf","abstract":"\"In this paper, we describe the system designed for the TREC 2017 Precision Medicine track by the University of Texas at Dallas (UTD) Human Language Technology Research In- stitute (HLTRI). Our system incorporates an aspect-based retrieval paradigm wherein each of the four structured com- ponents of the topic is cast as a separate aspect, along with two “hidden” aspects encoding the need that retrieved docu- ments be within the domain of precision medicine and that retrieved documents have a focus on treatment. To this end, we construct knowledge graph encoding the relationships be- tween drugs, genes, and mutations. Our experiments reveal that the aspect-based approach leads to improved quality of retrieved scientific articles and clinical trials.\"","keywords":"precision medicine, knowledge graph, information retrieval, question answering, medical informatics","bibtex":"@InProceedings{goodwin2017utd,\ntitle = {UTD HLTRI at TREC 2017: Precision Medicine Track},\nauthor = {Goodwin, Travis R. and Skinner, Michael A. and Harabagiu, Sanda M.},\nbooktitle = {Proceedings of the 26th Text REtrieval Conference},\nshortbooktitle={TREC '17},\nlocation= {Washington, DC, USA},\nyear = {2017},\nmonth = {November},\nurl_Paper = {papers/trec_2017_draft.pdf},\nurl_Slides = {papers/trec_2017_slides.pdf},\n abstract={\"In this paper, we describe the system designed for the TREC\n2017 Precision Medicine track by the University of Texas\nat Dallas (UTD) Human Language Technology Research In-\nstitute (HLTRI). Our system incorporates an aspect-based\nretrieval paradigm wherein each of the four structured com-\nponents of the topic is cast as a separate aspect, along with\ntwo “hidden” aspects encoding the need that retrieved docu-\nments be within the domain of precision medicine and that\nretrieved documents have a focus on treatment. To this end,\nwe construct knowledge graph encoding the relationships be-\ntween drugs, genes, and mutations. Our experiments reveal\nthat the aspect-based approach leads to improved quality of\nretrieved scientific articles and clinical trials.\"},\nkeywords = {precision medicine, knowledge graph, information retrieval, question answering, medical informatics}\n}\n\n","author_short":["Goodwin, T. R.","Skinner, M. A.","Harabagiu, S. M."],"key":"goodwin2017utd","id":"goodwin2017utd","bibbaseid":"goodwin-skinner-harabagiu-utdhltriattrec2017precisionmedicinetrack-2017","role":"author","urls":{" paper":"http://www.hlt.utdallas.edu/~travis/papers/trec_2017_draft.pdf"," slides":"http://www.hlt.utdallas.edu/~travis/papers/trec_2017_slides.pdf"},"keyword":["precision medicine","knowledge graph","information retrieval","question answering","medical informatics"],"downloads":0,"html":""},"search_terms":["utd","hltri","trec","2017","precision","medicine","track","goodwin","skinner","harabagiu"],"keywords":["precision medicine","knowledge graph","information retrieval","question answering","medical informatics"],"authorIDs":["5a2f21809abaa8bf3500003f"],"dataSources":["ea3q84ZXjZvjBmaC4"]}