• Corpus ID: 3900213

Team UKNLP at TREC 2017 Precision Medicine Track: A Knowledge-Based IR System with Tuned Query-Time Boosting

@inproceedings{Noh2017TeamUA,
  title={Team UKNLP at TREC 2017 Precision Medicine Track: A Knowledge-Based IR System with Tuned Query-Time Boosting},
  author={Jiho Noh and Ramakanth Kavuluru},
  booktitle={TREC},
  year={2017}
}
This paper describes the system architecture of the University of Kentucky Natural Language Processing (UKNLP) team’s entry for the TREC 2017 Precision Medicine Track. The goal of the challenge is to retrieve useful precision medicinerelated information (abstracts, clinical trials) for the given synthetic cancer patient cases, each of which consists of a neoplastic condition, genetic variants, demographic details, and any additional information (e.g., comorbidities). We explored query expansion… 
3 Citations

Figures and Tables from this paper

Designing a Novel Framework for Precision Medicine Information Retrieval

TLDR
This study investigates the application of the latest information retrieval and text mining techniques to PMIR and proposes three promising techniques: keyphrase extraction for indexing, hybrid query expansion including word embeddings, and retrieval results re-ranking with supervised regression analysis for PMIR.

An improved BM25 algorithm for clinical decision support in Precision Medicine based on co-word analysis and Cuckoo Search

  • Zicheng Zhang
  • Computer Science
    BMC Medical Informatics and Decision Making
  • 2021
TLDR
An improved version of BM25 that computes the scores of expanded words and co-word leading to a composite retrieval function, which is then optimized using the Cuckoo Search to achieve higher relevance and hence score of articles is proposed.

An Improved BM25 for Clinical Decision Support in Precision Medicine Based on Co-word Analysis and Cuckoo Search

TLDR
The proposed algorithm, an improved version of the BM25 algorithm, utilizes both co-word implementation and Cuckoo Search and verifies that the proposed algorithm produces better results on a large number of experimental sets.

References

SHOWING 1-6 OF 6 REFERENCES

FDUMedSearch at TREC 2015 Clinical Decision Support Track

TLDR
The FDUMedSearch team used Indri as the retrieval engine, which implemented query likelihood method as the baseline, and query expansion using Medical Subject Headings (MeSH), pseudo relevance feedback and classification were used to enhance the retrieval performance.

ECNU at 2015 CDS Track: Two Re-ranking Methods in Medical Information Retrieval

This paper summarizes our work on the TREC 2015 Clinical Decision Support Track. We present a customized learningto-rank algorithm and a query term position based re-ranking model to better satisfy

Bridging Language Modeling and Divergence from Randomness Models: A Log-Logistic Model for IR

TLDR
The first normalization principle of DFR is shown to be necessary to make the model compliant with retrieval constraints, and it is shown that the log-logistic distribution can be used to derive a simplified DFR model, which contains Language Models (LM) with Jelinek-Mercer smoothing.

Probability models for information retrieval based on divergence from randomness

TLDR
This thesis devises a novel methodology based on probability theory, suitable for the construction of term-weighting models of Information Retrieval, and shows that even language modelling approach can be exploited to assign term-frequency normalization to the models of divergence from randomness.

Information-based models for ad hoc IR

TLDR
A long-standing hypothesis in IR, namely the fact that the difference in the behaviors of a word at the document and collection levels brings information on the significance of the word for the document, is shown to lead to simpler and better models.

FDUMedSearch at TREC 2015

  • Clinical Decision Support Track. TREC,
  • 2015