350 likes | 380 Views
Chapter 3 Retrieval Evaluation. Modern Information Retrieval Ricardo Baeza-Yates Berthier Ribeiro-Neto. Hsu Yi-Chen, NCU MIS 88423043. Outline. Introduction Retrieval Performance Evaluation Recall and precision Alternative measures Reference Collections TREC Collection
E N D
Chapter 3Retrieval Evaluation Modern Information Retrieval Ricardo Baeza-Yates Berthier Ribeiro-Neto Hsu Yi-Chen, NCU MIS 88423043
Outline • Introduction • Retrieval Performance Evaluation • Recall and precision • Alternative measures • Reference Collections • TREC Collection • CACM&ISI Collection • CF Collection • Trends and Research Issues
Introduction • Type of evaluation • Functional analysis phase, and Error analysis phase • Performance evaluation • Performance of the IR system • Performance evaluation • Response time/space required • Retrieval performance evaluation • The evaluation of how precise is the answer set
Retrieval performance evaluation for IR system Goodness of retrieval strategy S = the similarity between Set of retrieval documents by S Set of relevant documents provided by specialists quantified by Evaluation measure
Retrieval Performance Evaluation(Cont.) • 評估以batch query 為主的IR 系統 Relevant Docs In Answer Set |Ra| Recall=|Ra|/|R| Precision=|Ra|/|A| collection Answer Set |A| Relevant Docs |R| Sorted by relevance
Precision versus recall curve • Rq={d3,d5,d9,d25,d39,d44,d56,d89,d123} Ranking for query q: 11.d38 12.d48 13.d250 14.d11 15.d3* 1.d123* 2.d84 3.d56* 4.d6 5.d8 6.d9* 7.d511 8.d129 9.d187 10.d25* • 100% at10% • 66% at 20% • 50% at 30% • Usally based on 11 standard recall levels:0%,10%,..100%
Precision versus recall curve • For a single query Fig3.2
計算多個query的平均效能 • P(r)= Σ(Pi(r)/Nq) • P(r)=average precision at the recall leval • Nq=number of queries used • Pi(r)=the precision at recall level r for the i-th query i=Nq i=1
Interpolated precision • Rq={d3,d56,d129} • Let rj,j={0,1,2,…,10},be a reference to the j-th standard recall level • P(rj)=max ri≦r≦rj+1P(r)
Single Value Summaries • 之前的average precision versus recall: • 比較retrieval algorithms over a set of example queries • But! Individual query的performance也很重要,因為: • Average precision可能會隱藏演算法中不正常的部分 • 可能需要知道,兩個演算法中,對某特定query的performance為何 • 解決方法: • 考慮每一個query的single precision value • The single value should be interpreted as a summary of the corresponding precision versus recall curve • 通常 ,single value summary被用來當作某一個recall level 的precision值
Average Precision at Seen Relevant Documents • Averaging the precision figures obtained after each new relevant document is observed. • F3.2,(1+0.66+0.5+0.4+0.3)/5=0.57 • 此方法對於很快找到相關文件的系統是相當有利的(相關文件被排在越前面,precision值越高)
R-Precision • Computing the precision at the R-th position in the ranking(在R 篇文章中出現相關文章數目的比例) • R:the total number of relevant documents of the current query(total number in Rq) • Fig3.2:R=10,value=0.4 • Fig3.3,R=3,value=0.33 • 易於觀察每一個單一query的演算法performance
Precision Histograms • 利用長條圖比較兩個query的R-precision值 • RPA/B(i )=RPA(i )-RPB(i ) • RPA(i),RPB(i):R-precision value of A,B for i-th query • Compare the retrieval performance history of two algorithms through visual inspection
Summary Table Statistics • 將所有query相關的single value summary 放在table中 • 如the number of queries , • total number of documents retrieved by all queries, • total number of relevant documents were effectively retrieved when all queries are considered • Total number of relevant documents retrieved by all queries…
Precision and Recall 的適用性 • Maximum recall值的產生,需要知道所有文件相關的背景知識 • Recall and precision是相對的測量方式,兩者要合併使用比較適合。 • Measures which quantify the informativeness of the retrieval process might now be more appropriate • Recall and precision are easy to define when a linear ordering of the retrieved documents is enforced
1 1 b2 1 F(j)= r(j) P(j) r(j) P(j) 2 1+b2 + + E(j)=1- Alternative Measures • The Harmonic Mean • ,介於0,1 • The E Measure-加入喜好比重 • b=1,E(j)=F(j) • b>1,more interested in precision • b<1,more interested in recall
User-Oriented Measure • 假設:Query與使用者有相關,不同使用者有不同的relevant docs • coverage=|Rk|/|U| • Novelty=|Ru|/|Ru|+|Rk| • Coverage越高,系統找到使用者期望的文件越多 • Noverlty越高,系統找到許多使用者之前不知道相關的文件越多
User-Oriented Measure(cont.) • relative recall:系統找到的相關文章數佔使用者預期找到的文章數比例 • (|Ru|+|Rk|)/ |U| • Recall effort:使用者期望找到的相關文章數佔符合使用者期望的相關文章數(the number of documents examined in an attempt to find the expected relevant documents) • |U|/|Rk|
Reference Collection • 用來作為評估IR系統reference test collections • TIPSTER/TREC:量大,實驗用 • CACM,ISI:歷史意義 • Cystic Fibrosis :small collections,relevant documents由專家研討後產生
IR system遇到的批評 • Lacks a solid formal framework as a basic foundation • 無解!一個文件是否與查詢相關,是相當主觀的! • Lacks robust and consistent testbeds and benchmarks • 較早,發展實驗性質的小規模測試資料 • 1990後,TREC成立,蒐集上萬文件,提供給研究團體作IR系統評量之用
TREC(Text REtrieval Conference) • Initiated under the National Institute of Standards and Technology(NIST) • Goals: • Providing a large test collection • Uniform scoring procedures • Forum • 7th TREC conference in 1998: • Document collection:test collections,example information requests(topics),relevant docs • The benchmarks tasks
The Documents Collection • 由SGML編輯 <doc> <docno>WSJ880406-0090</docno> <hl>AT&T Unveils Services to Upgrade Phone Networks Under Global Plan</hl> <author>Janet GuyonWSJ Staff)</author> <dateline>New York</dateline> <text> American Telephone & Telegrapj Co. introduced the first of a newgeneration of phone service with broad… </text> </doc>
The Example Information Requests(Topics) • 用自然語言將資訊需求描述出來 • Topic number:給不同類型的topics <top> <num> Number:168 <title>Topic:Financing AMTRAK <desc>Description: ….. <nar>Narrative:A ….. </top>
The relevant Documents for Each Example Information Request • The set of relevant documents for each topic obtained from a pool of possible relevant documents • Pool:由數各參與的 IR系統中所找到的相關文件,依照相關性排序後的前K個文章。 • K通常為100 • 最後透過人工鑑定,判斷是否為相關文件 • ->pooling method • 相關文件有數個組合的pool取得 • 不在pool內的文件視為不相關文件
The (Benchmark)Tasks at the TREC Conferences • ad hoc task: • Receive new requests and execute them on a pre-specified document collection • routing task • Receive test info. Requests,two document collections • first doc:training and tuning retrieval algorithm • Second doc:testing the tuned retrieval algorithm
Other tasks: • *Chinese • Filtering • Interactive • *NLP(natural language procedure) • Cross languages • High precision • Spoken document retrieval • Query Task(TREC-7)
Evaluation Measures at the TREC Conferences • Summary table statistics • Recall-precision • Document level averages* • Average precision histogram
The CACM Collection • Small collections about computer science literature • Text of doc • structured subfields • word stems from the title and abstract sections • Categories • direct references between articles:a list of pairs of documents[da,db] • Bibliographic coupling connections:a list of triples[d1,d2,ncited] • Number of co-citations for each pair of articles[d1,d2,nciting] • A unique environment for testing retrieval algorithms which are based on information derived from cross-citing patterns
The ISI Collection • ISI 的test collection是由之前在ISI(Institute of Scientific Information) 的Small組合而成 • 這些文件大部分是由當初Small計畫中有關cross-citation study中挑選出來 • 支持有關於terms和cross-citation patterns的相似性研究
The Cystic Fibrosis Collection • 有關於“囊胞性纖維症”的文件 • Topics和相關文件由具有此方面在臨床或研究的專家所產生 • Relevance scores • 0:non-relevance • 1:marginal relevance • 2:high relevance
Characteristics of CF collection • Relevance score均由專家給定 • Good number of information requests(relative to the collection size) • The respective query vectors present overlap among themselves • 利用之前的query增加檢索效率
Trends and Research Issues • Interactive user interface • 一般認為feedback的檢索可以改善效率 • 如何決定此情境下的評估方式(Evaluation measures)? • 其它有別於precise,recall的評估方式研究