1. NCCU Academic Hub
  2. 學術產出
  3. 資訊學院
  4. 期刊論文
  5. Item

學術產出-期刊論文

文章檢視/開啟

書目匯出

Google ScholarTM

政大圖書館

引文資訊

TAIR相關學術產出

題名 Query-level Loss Functions for Information Retrieval
作者 蔡銘峰
Qin,Tao ; Zhang,Xu-Dong ; Tsai,Ming-Feng ; Wang,De-Sheng ; Liu,Tie-Yan; Li,Hang
貢獻者 資科系
關鍵詞 Information retrieval; Learning to rank; Query-level loss function; Rank Cosine
日期 2008
上傳時間 11-九月-2014 10:43:37 (UTC+8)
摘要 Many machine learning technologies such as support vector machines, boosting, and neural networks have been applied to the ranking problem in information retrieval. However, since originally the methods were not developed for this task, their loss functions do not directly link to the criteria used in the evaluation of ranking. Specifically, the loss functions are defined on the level of documents or document pairs, in contrast to the fact that the evaluation criteria are defined on the level of queries. Therefore, minimizing the loss functions does not necessarily imply enhancing ranking performances. To solve this problem, we propose using query-level loss functions in learning of ranking functions. We discuss the basic properties that a query-level loss function should have and propose a query-level loss function based on the cosine similarity between a ranking list and the corresponding ground truth. We further design a coordinate descent algorithm, referred to as RankCosine, which utilizes the proposed loss function to create a generalized additive ranking model. We also discuss whether the loss functions of existing ranking algorithms can be extended to query-level. Experimental results on the datasets of TREC web track, OHSUMED, and a commercial web search engine show that with the use of the proposed query-level loss function we can significantly improve ranking accuracies. Furthermore, we found that it is difficult to extend the document-level loss functions to query-level loss functions.
關聯 Information Processing and Management, 44(2),838-855
資料類型 article
dc.contributor 資科系en_US
dc.creator (作者) 蔡銘峰zh_TW
dc.creator (作者) Qin,Tao ; Zhang,Xu-Dong ; Tsai,Ming-Feng ; Wang,De-Sheng ; Liu,Tie-Yan; Li,Hangen_US
dc.date (日期) 2008en_US
dc.date.accessioned 11-九月-2014 10:43:37 (UTC+8)-
dc.date.available 11-九月-2014 10:43:37 (UTC+8)-
dc.date.issued (上傳時間) 11-九月-2014 10:43:37 (UTC+8)-
dc.identifier.uri (URI) http://nccur.lib.nccu.edu.tw/handle/140.119/69777-
dc.description.abstract (摘要) Many machine learning technologies such as support vector machines, boosting, and neural networks have been applied to the ranking problem in information retrieval. However, since originally the methods were not developed for this task, their loss functions do not directly link to the criteria used in the evaluation of ranking. Specifically, the loss functions are defined on the level of documents or document pairs, in contrast to the fact that the evaluation criteria are defined on the level of queries. Therefore, minimizing the loss functions does not necessarily imply enhancing ranking performances. To solve this problem, we propose using query-level loss functions in learning of ranking functions. We discuss the basic properties that a query-level loss function should have and propose a query-level loss function based on the cosine similarity between a ranking list and the corresponding ground truth. We further design a coordinate descent algorithm, referred to as RankCosine, which utilizes the proposed loss function to create a generalized additive ranking model. We also discuss whether the loss functions of existing ranking algorithms can be extended to query-level. Experimental results on the datasets of TREC web track, OHSUMED, and a commercial web search engine show that with the use of the proposed query-level loss function we can significantly improve ranking accuracies. Furthermore, we found that it is difficult to extend the document-level loss functions to query-level loss functions.en_US
dc.format.extent 258907 bytes-
dc.format.mimetype application/pdf-
dc.language.iso en_US-
dc.relation (關聯) Information Processing and Management, 44(2),838-855en_US
dc.subject (關鍵詞) Information retrieval; Learning to rank; Query-level loss function; Rank Cosineen_US
dc.title (題名) Query-level Loss Functions for Information Retrievalen_US
dc.type (資料類型) articleen