COMP6115 Text Processing Assignment Understand Matrials 输 1- 章： documents.txt 内容是 堆 章 具体内容包括 title author(s) abstract although some of these (esp. abstract) may be absent for a given record. 输 2-查询：queries.txt 完整查询句 ，TODO：解析查询句 参照 于衡量匹配结果的标准答案： cacm gold std.txt a ‘gold standard’ identifying the documents that have been judged relevant to each query. 脚本/code : eval ir.py calculates system performance scores, by comparing the gold standard to a system results file, of which an example is provided as example_results_file.txt . 执 代码 “python eval ir.py cacm gold std.txt example results file.txt” 初始模版代码，如下： “”” ————————————————————————— —– USE: python (options) keyfile response ACTION: computes IR system performance measures, given input files: * ‘keyfile’ – a “gold standard” indicating the documents that are relevant to each query, and * ‘response’ – the documents retrieved for each query by the system. MAJOR OPTIONS: -h : print this help message -n INT : only consider the first INT responses for each query SPECIAL OPTIONS: -q : print scores for each individual question (not just global averages) -f : print summary scores in “flat”” mode (i.e. as numbers on single line) -F : print terse flat summary – shows only P
