A study of relevance feedback techniques in interactive multilingual information access
| DOI | https://doi.org/10.1108/07378831211266645 |
| Published date | 31 August 2012 |
| Date | 31 August 2012 |
| Pages | 523-544 |
| Author | Dan Wu,Daqing He,Xiaomei Xu |
| Subject Matter | Information & knowledge management,Library & information science |
REGULAR PAPER
A study of relevance feedback
techniques in interactive
multilingual information access
Dan Wu
School of Information Management, Wuhan University, Wuhan, China
Daqing He
School of Information Sciences, University of Pittsburgh, Pittsburgh,
Pennsylvania, USA and International Collaborative Academy of Library and
Information Science, Wuhan University, China, and
Xiaomei Xu
School of Information Management, Wuhan University, Wuhan, China
Abstract
Purpose – With the vast amount of multilingual information available online, it becomes
increasingly critical for libraries to use various multilingual information access techniques in order to
effectively support patrons’ online information requests. However, this is still a relatively
under-explored area. This paper aims to study the effectiveness and the adoptability of query
expansion and translation enhancement in the context of interactive multilingual information access.
Design/methodology/approach – Relying on an interactive multilingual information access
system called ICE-TEA, the authors conducted a controlled experiment (English-to-Chinese
translation) involving human subjects to assess the retrieval effectiveness, analyzed the collected
search logs to examine users’ behavior, and employed pre- and post-questionnaires to obtain users’
opinions about the system.
Findings – The results confirm that significant improvement in retrieval effectiveness can be
achieved by combining query expansion with translation enhancement (as compared to a case when
there is no relevance feedback). However, users’ ability to understand, interact with and even perceive
the complex process of searches involving the combination of query expansion and translation
enhancement may greatly impact the effectiveness of the techniques. The results also confirm that
human-generated queries were short queries, which calls for careful consideration of how longer
queries perform in real search because many search engines rely on longer and more complex queries.
Originality/value – This study examines two important relevance feedback techniques in the
context of human-involved multilingual information access. This study is a valuable addition to the
information seeking behaviour literature.
Keywords Relevance feedback,Interactive cross-languageinformation access,
User-involvedcontrolled experiments, Referenceservices, Information
Paper type Research paper
The current issue and full text archive of this journal is available at
www.emeraldinsight.com/0737-8831.htm
This work was supported by the Social Science Foundation of the Chinese Education Ministry
under agreement 09YJC870022, by Wuhan International Science and Technology Cooperation
Fund under agreement 201070934337, by the 3rd Special Award of the China Postdoctoral
Science Foundation under agreement 201003497, and by the National Science Foundation of the
USA under agreement NSF/IIS 1052773.
Relevance
feedback
techniques
523
Received January 2012
Revised January 2012
Accepted May 2012
Library Hi Tech
Vol. 30 No. 3, 2012
pp. 523-544
qEmerald Group Publishing Limited
0737-8831
DOI 10.1108/07378831211266645
1. Introduction
This is a fascinating time for library services. For the first time, it is possible to build
large, diverse, and universal access library services using collections of digital
information; and then delivering them over an information infrastructure on a global
scale. By drawing on heterogeneous resources, libraries carry out tasks that demand
more and more multimedia, multicultural, and multilingual information services.
Multilingual communication enables the dissemination of information beyond the
boundaries of languages. Interactive Multilingual Information Access (MLIA) refers to
a process in which a user and a system collaborate to find documents that satisfy
his/her information needs, regardless of the language in which those documents are
created. As a complex processing effort, interactive MLIA can be modeled as a cascad e
of five stages with the possibility of reverse ordered stages (Oard and Diekema, 1998).
Figure 1 shows that four of these five stages involved the user working with the
retrieval engine; only the “Ranked Retrieval” stage is based solely on the output from
the retrieval engine.
Researchers who work on interactive MLIA have mainly concentrated on the
interaction and collaboration aspects of the whole search process, paying attention
primarily to the query translation stage and the document selection and examination
stages. As a unique stage in interactive MLIA (in comparison to the stages in
interactive monolingual information access), the research questions associated with
query translation have focused on how to translate the input queries manually,
automatically or in a user-assisted fashion. Some of the important examples include
several years of interactive experiments in Cross-Language Evaluation Forum (CLEF)
dedicated to this topic (Oard and Gonzalo, 2001; Gonzalo and Oard, 2002; Oard and
Gonzalo, 2003), and a number of cross language retrieval systems built based on
various query translation strategies (He et al., 2003; Petrelli et al., 2006). The studies of
document selection and examination look at different translation strategies for
supporting searchers’ selecting and reviewing relevant documents (Oard et al., 2004).
Figure 1.
Steps in interactive
multilingual information
access
LHT
30,3
524
To continue reading
Request your trial