Difference between revisions of "Obvio"

From Knoesis wiki
Jump to: navigation, search
(Datasets and Experimental Results)
(Datasets and Experimental Results)
Line 39: Line 39:
 
### [http://knoesis.wright.edu/researchers/delroy/projects/swanson-rfo/swanson-rfo-text-ascii-baseline-1.zip ASCII text with end-of-line text wrapping fixed]  
 
### [http://knoesis.wright.edu/researchers/delroy/projects/swanson-rfo/swanson-rfo-text-ascii-baseline-1.zip ASCII text with end-of-line text wrapping fixed]  
 
### [http://knoesis.wright.edu/researchers/delroy/projects/swanson-rfo/swanson-rfo-medline-format-baseline-1.zip Text in Medline format for parsing by SemRep]
 
### [http://knoesis.wright.edu/researchers/delroy/projects/swanson-rfo/swanson-rfo-medline-format-baseline-1.zip Text in Medline format for parsing by SemRep]
 +
### [http://knoesis.wright.edu/researchers/delroy/projects/swanson-rfo/swanson-rfo-semrep-relations-baseline-1.zip SemRep Relations Output]
 
## Baseline (B2) <br />  
 
## Baseline (B2) <br />  
 
# Experimental Results
 
# Experimental Results

Revision as of 21:17, 21 February 2012

Obvio (spanish for obvious) is the name of the project on semantics-based techniques for Literature-Based Discovery (LBD) using Biomedical Literature. The goal of Obvio is to uncover hidden connections between concepts in text, thereby leading to hypothesis generation from publicly available scientific knowledge sources.

Overview

Obvio is driven by assertions extracted from structured text (called semantic predications) as well as assertions obtained from structured knowledge sources (such as the UMLS).

Project Team

Graduate Students: Delroy Cameron, Tu Danh, Sreeram Vallabhaneni, Hima Yalamanchili
External Collaborators: Olivier Bodenreider, Thomas C. Rindflesch, Ramakanth Kavuluru, Pablo N. Mendes
Faculty: Krishnaprasad Thirunarayan, Amit P. Sheth (Advisor)

Application

Question Answering

Reachability

One application of semantic predications is in the field on biomedical Question Answering(QA). The QA task put forth by the Text REtrieval Conferences (TREC) offer an opportunity to determine whether semantic predications can yielded relevant information given complex information needs.

Literature-based Discovery (LBD)

Swanson's Hypotheses

Now that techniques are available for predication extraction, automating Swanson's hypothesis generation using the MEDLINE corpus becomes particularly appealing. In particular, the extent of combinatorial explosion presents a major limitation in using the predications to recover the original paths suggested by Swanson. At the same time however, many alternative and potentially interesting connects may also exist, not limited to the length and types suggested by Swanson. In this project we intend to (semi)automatically discover interesting paths between concepts in closed-discovery.

RS-DFO Hypothesis

Various datasets and experimental results are available for download and reuse

Datasets and Experimental Results
  1. Dataset
    1. Baseline (B1)
      1. Original PDFs of the 65 articles cited by Swanson's RS-DFO paper (30.5MB)
      2. ASCII text with end-of-line text wrapping fixed
      3. Text in Medline format for parsing by SemRep
      4. SemRep Relations Output
    2. Baseline (B2)
  2. Experimental Results
    1. Experiment I (Subgraph Comparisons)
    2. Experiment II (Subgraph Comparisons)
    3. Stand-alone Subgraphs
  3. Vascular Reactivity Dataset
    1. SemRep Relations
    2. Manually added Predications

Publications

  1. D. Cameron, R. Kavuluru, O. Bodenreider, P. N. Mendes, A. P. Sheth, K. Thirunarayan, Semantic Predications for Complex Information Needs in Biomedical Literature, 5th International Conference on Bioinformatics and Biomedicine BIBM2011, Atlanta GA, November 12-15, 2011 (acceptance rate=19.4%)


See Also

Swanson's Hypotheses
Reachability

Contact: Delroy Cameron