Download presentation
Presentation is loading. Please wait.
1
Modern Information Retrieval
Chapter 3 Retrieval Evaluation
2
The most common measures of system performance are time and space
an inherent tradeoff Data retrieval time and space indexing Information retrieval precision of the answer set also important
4
evaluation considerations
query with/without feedback query interface design real data/synthetic data real life/laboratory environment repeatability and scalability
5
recall and precision recall: fraction of relevant documents which has been retrieved precision: fraction of retrieved documents which is relevant
6
can we precisely compute precisions? can we precisely compute recalls?
7
precision versus recall curve: a standard evaluation strategy
9
interpolation procedure for generating the 11 standard recall levels
Rq={d3,d56,d129} where j is in {0,1,2,…,10} and P(r) is a known precision
11
to evaluate the retrieval strategy over all test queries, the precisions at each recall level are averaged
12
another approach: compute average precision at given relevant document cutoff values
advantages?
13
single value summary for each query
average precision at seen relevant documents example in Figure 3.2 favor systems which retrieve relevant documents quickly can have a poor overall recall performance R-precision R: total number of relevant documents examples in Figures 3.2 and 3.3
14
precision histogram
15
combining recall and precision
the harmonic mean it assumes a high value only when both recall and precision are high
16
the E measure b=1, complement of the harmonic mean
b>1, the user is more interested in precision b<1, the user is more interested in recall
17
user-oriented measures
18
coverage ratio: fraction of the documents known to be relevant which has been retrieved
the system finds the relevant documents the user expected to see
19
novelty ratio: fraction of the relevant documents retrieved which was previously unknown to the user
the system reveals new relevant documents previously unknown to the user
20
relative recall: the ratio between the number of relevant documents found and the number of relevant documents the user expected to find relative recall= when the relative recall equals to 1 (the user finds enough relevant documents), the user stops searching
21
recall effort: the ratio between the number of relevant documents the user expected to find and the number of documents examined in an attempt to find the expected relevant documents research in IR lack a solid formal framework lack robust and consistent testbeds and benchmarks Text REtrieval Conference
22
retrieval techniques methods using automatic thesauri sophisticated term weighting natural language techniques relevance feedback advanced pattern matching document collection over 1 million documents newspaper, patents, etc. topics in natural language conversion done by the system
23
relevant documents the pooling method: for each topic, collect the top k documents generated by each participating system and decide their relevance by human assessors the benchmark tasks ad hoc task filtering task Chinese cross languages spoken document retrieval high precision very large collection
24
evaluation measures summary table statistics: number of documents retrieved, number of relevant documents retrieved, number of relevant documents not retrieved, etc. recall-precision averages document level averages: average precision at seen relevant documents average precision histogram
Similar presentations
© 2024 SlidePlayer.com. Inc.
All rights reserved.