Smoothing functions for automatic relevance feedback in information retrieval

Amo, P.; Ferreras, F.L.; Cruz, Francisco; Rosa, Massimo La

doi:10.1109/dexa.2000.875013

Cited by 9 publications

(5 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…He also suggests bringing query to each document before cluster as an improvement. Amo [1] considers that treating the top N documents of the initial retrieval results as same will lose some useful information. Some rank index of the initial results will be not used.…”

Section: Related Workmentioning

confidence: 99%

Improving Relevance Feedback via Using Support Vector Machines

Chen

Yang

2011

AMR

View full text Add to dashboard Cite

Traditional relevance feedback technique could help improve retrieval performance. It usually utilize the most frequent terms in the relevant documents to enrich the user’s initial query. We re-examine this method and find that many expansion terms identified in traditional approaches are indeed unrelated to the query and harmful to the retrieval. This paper introduces a Support Vector Machines Based method to improve the retrieval results. Firstly, the classifier is trained on the feedback documents. Then, we can utilize this classifier to classify the rest of the documents and move relevant documents to the front of irrelevant documents. This new approach avoids modifying the initial query, so it’s a new direction for the relevance feedback techniques. Our Experiments on TREC dataset demonstrate that retrieval effectiveness can be improved more than 24.37% when our proposed approach is used.

show abstract

Section: Related Workmentioning

confidence: 99%

Improving Relevance Feedback via Using Support Vector Machines

Chen

Yang

2011

AMR

View full text Add to dashboard Cite

show abstract

“…As relevant visual features we can think here, for instance, of a particular shades of green and their spatial combination with specific shades of blue or gray colors, specific texture of clouds, etc. Although the optimization of the relevance feedback procedure at the cognitive level in terms of convergence speed and precision has not been reached yet, considerable work has been done toward this optimization [17][18][19][20].…”

Section: Image Databasementioning

confidence: 99%

<title>Video and image retrieval beyond the cognitive level: the needs and possibilities</title>

Hanjalic

2001

SPIE Proceedings

View full text Add to dashboard Cite

The worldwide research efforts in the area of image and video retrieval have concentrated so far on increasing the efficiency and reliability of extracting the elements of image and video semantics and so on improving the search and retrieval performance at the cognitive level of content abstraction. At this abstraction level, the user is searching for "factual" or "objective" content such as image showing a panorama of San Francisco, an outdoor or an indoor image, a broadcast news report on a defined topic, a movie dialog between the actors A and B or the parts of a basketball game showing fast breaks, steals and scores. These efforts, however, do not address the retrieval applications at the so-called affective level of content abstraction where the "ground truth" is not strictly defined. Such applications are, for instance, those where subjectivity of the user plays the major role, e.g. the task of retrieving all images that the user "likes most", and those that are based on "recognizing emotions" in audiovisual data. Typical examples are searching for all images that "radiate happiness", identifying all "sad" movie fragments and looking for the "romantic landscapes", "sentimental" movie segments, "movie highlights" or "most exciting" moments of a sport event. This paper discusses the needs and possibilities for widening the current scope of research in the area of image and video search and retrieval in order to enable applications at the affective level of content abstraction.

show abstract

“…通常认为相关反馈的研究源于 Rocchio,1971 年他针对文本信息检索基于向量空间模型在 SMART 系统中完成了最初的相关反馈实验.无论是早期实验还是近几届的 TREC 实验都说明相关反馈可以提高检索效率 [1] .国内也开展了相关反馈技术的研究 [2−5] ,研究结果都显示了相关反馈技术能够有效提高查准率、查全率.伪反馈又称为局部反馈、盲反馈,它假设初始检索结果的前面若干篇文档是相关的,然后利用标准的相关反馈过程进行查询扩展.多次 TREC 评测会议表明,伪反馈是一种简单但十分有效的查询扩展技术.伪反馈方法的一个重大缺点就是可能在查询扩展期间产生"查询主题漂移".目前主要采用两种思路解决查询漂移问题,一是对初始检索结果进行调整,使用于反馈的文档都是相关文档 [6,7] ;二是先检索结果聚类再进行查询扩展 [8−11] .国内对此问题也进行了积极的研究 [12−14] .隐式反馈方法中用户不主动参与反馈,但是系统仍需要从用户的浏览行为中分析得到一些有用的信息用来确定用户兴趣模式,从而推理出描述用户查询需求的表达式,并据此进行检索.在查询扩展中利…”

unclassified

Structural Query Expansion Based on Weighted Query Term for XML Documents

Wan¹,

Liu²

2008

Journal of Software

View full text Add to dashboard Cite

Abstract:The main reason of low precision in information retrieval (IR) is that it is difficult for the users to submit a precise query expression for their query intensions. Furthermore, XML documents have characteristics not only in the content, but also in its structure. Therefore it is more difficult for users to submit precise query expressions. In order to solve this problem, this paper puts forward a new query expansion method based on relevance feedback. It can help users to construct a content and structure query expression which can satisfy users' intentions. This method includes two steps. The first step is to expand keywords for finding the weighted keyword which can represent the user's intentions. The second step is structural expansion based on the weighted keywords.Finally a full-edged content-structure query is formalized. Experimental results show that the method can obtain better retrieval results. The average precision of prec@10 and prec@20 is 30% higher than the original query.

show abstract

Smoothing functions for automatic relevance feedback in information retrieval

Cited by 9 publications

References 7 publications

Improving Relevance Feedback via Using Support Vector Machines

Improving Relevance Feedback via Using Support Vector Machines

<title>Video and image retrieval beyond the cognitive level: the needs and possibilities</title>

Structural Query Expansion Based on Weighted Query Term for XML Documents

Contact Info

Product

Resources

About