Text REtrieval Conference (TREC)
|
Organization Name: University Hospital of Geneva - EPFL | Run ID: tgIIhugLASt |
Section 1.0 System Summary and Timing |
---|
Section 1.1 System Information |
Hardware Model Used for TREC Experiment:Intel Pentium System Use:SHARED Total Amount of Hard Disk Storage:480 Gb Total Amount of RAM:2000 MB Clock Rate of CPU:2.0 MHz |
Section 1.2 System Comparisons |
Amount of developmental "Software Engineering":NONE List of features that are not present in the system, but would have been beneficial to have:Gene and protein entity recognition. List of features that are present in the system, and impacted its performance, but are not detailed within this form: |
Section 2.0 Construction of Indices, Knowledge Bases, and Other Data Structures |
---|
Length of the stopword list:368 words Type of Stemming:PORTER Controlled Vocabulary:YES Term weighting:YES
Phrase discovery:YES
Type of Spelling Correction:NONE Manually-Indexed Terms:NO Proper Noun Identification:NO Syntactic Parsing:YES Tokenizer:YES Word Sense Disambiguation:NO Other technique: Additional comments: |
Section 3.0 Statistics on Data Structures Built from TREC Text |
---|
Section 3.1 First Data Structure |
Structure Type:INVERTED INDEX Type of other data structure used: Brief description of method using other data structure: Total storage used:136 Gb Total computer time to build:500 hours Automatic process:YES Manual hours required:hours Type of manual labor:NONE Term positions used:NO Only single terms used:NO Concepts (vs. single terms) represented:YES
Type of representation:stems + MeSH terms Auxilary files used:YES
Additional comments: |
Section 3.2 Second Data Structure |
Structure Type:CLUSTER Type of other data structure used:Classifier Brief description of method using other data structure:see comment Total storage used:0.2 Gb Total computer time to build:0.5 hours Automatic process:YES Manual hours required:hours Type of manual labor:NONE Term positions used: Only single terms used:NO Concepts (vs. single terms) represented:NO
Type of representation:n-grams Auxilary files used:YES
Additional comments:Argumentative features: ability to classify sentences into 4 classes (PURPOSE, METHODS, RESULTS, CONCLUSION). |
Section 3.3 Third Data Structure |
Structure Type: Type of other data structure used: Brief description of method using other data structure: Total storage used:Gb Total computer time to build:hours Automatic process: Manual hours required:hours Type of manual labor:NONE Term positions used: Only single terms used: Concepts (vs. single terms) represented:
Type of representation: Auxilary files used:
Additional comments: |
Section 4.0 Data Built from Sources Other than the Input Text |
---|
File type:OTHER Domain type:DOMAIN INDEPENDENT Total Storage:0.2 Gb Number of Concepts Represented:4 concepts Type of representation:OTHER Automatic or Manual:AUTOMATIC
Type of Manual Labor used:NONE Additional comments:These internally-built files are MedLine citations (about 15000) used to train the argumentative classifier. |
File is:OTHER Total Storage:0.7 Gb Number of Concepts Represented:19636 concepts Type of representation:OTHER Additional comments:This externally-built resource comes from the UMLS. It uses MeSH terms as indexing units. |
Section 5.0 Computer Searching |
---|
Average computer time to search (per query): 5000 CPU seconds |
Times broken down by component(s): |
Section 5.1 Searching Methods |
Vector space model:YES Probabilistic model: Cluster searching: N-gram matching:YES Boolean matching: Fuzzy logic: Free text scanning: Neural networks: Conceptual graphic matching: Other: Additional comments: |
Section 5.2 Factors in Ranking |
Term frequency:YES Inverse document frequency:YES Other term weights: Semantic closeness: Position in document: Syntactic clues:YES Proximity of terms: Information theoretic weights: Document length: Percentage of query terms which match: N-gram frequency:YES Word specificity: Word sense frequency: Cluster distance: Other: Additional comments: |
Section 6.0 Query Construction |
---|
Section 6.1 Automatically Built Queries for Ad-hoc Tasks |
Topic fields used: OTHER Average computer time to build query 10 CPU seconds Term weighting (weights based on terms in topics): YES Phrase extraction from topics: YES Syntactic parsing of topics: YES Word sense disambiguation: Proper noun identification algorithm: Tokenizer: YES Expansion of queries using previously constructed data structures: NO Automatic addition of: NONE |
Section 6.2 Manually Constructed Queries for Ad-hoc Tasks |
Topic fields used: Average time to build query? minutes Type of query builder: OTHER Tool used to build query: NONE Method used in intial query construction? BOOLEAN CONNECTORS Total CPU time for all iterations: seconds Clock time from initial construction of query to completion of final query: minutes Average number of iterations: Average number of documents examined per iteration: Minimum number of iterations: Maximum number of iterations: The end of an iteration is determined by: Automatic term reweighting from relevant documents: Automatic query expansion from relevant documents: Other automatic methods: Manual methods used: |
Disclaimer: Contents of this online document are not necessarily the official views of, nor endorsed by the U.S. Government, the Department of Commerce, or NIST. |