Automatic query expansion : a structural linguistic perspective

A user’s query is considered to be an imprecise description of their information need. Automatic query expansion is the process of reformulating the original query with the goal of improving retrieval effectiveness. Many successful query expansion techniques ignore information about the dependencies that exist between words in natural language. However, more recent approaches have demonstrated that by explicitly modeling associations between terms significant improvements in retrieval effectiveness can be achieved over those that ignore these dependencies. State-of-the-art dependency-based approaches have been shown to primarily model syntagmatic associations. Syntagmatic associations infer a likelihood that two terms co-occur more often than by chance. However, structural linguistics relies on both syntagmatic and paradigmatic associations to deduce the meaning of a word. Given the success of dependency-based approaches and the reliance on word meanings in the query formulation process, we argue that modeling both syntagmatic and paradigmatic information in the query expansion process will improve retrieval effectiveness. This article develops and evaluates a new query expansion technique that is based on a formal, corpus-based model of word meaning that models syntagmatic and paradigmatic associations. We demonstrate that when sufficient statistical information exists, as in the case of longer queries, including paradigmatic information alone provides significant improvements in retrieval effectiveness across a wide variety of data sets. More generally, when our new query expansion approach is applied to large-scale web retrieval it demonstrates significant improvements in retrieval effectiveness over a strong baseline system, based on a commercial search engine.

An Information Theoretic Approach to Automatic Query Expansion

International audience

A Correlation Analysis on LSA and HAL Semantic Space Models

In this paper, we compare a well-known semantic spacemodel, Latent Semantic Analysis (LSA) with another model, Hyperspace Analogue to Language (HAL) which is widely used in different area, especially in automatic query refinement. We conduct this comparative analysis to prove our hypothesis that with respect to ability of extracting the lexical information from a corpus of text, LSA is quite similar to HAL. We regard HAL and LSA as black boxes. Through a Pearsonrsquos correlation analysis to the outputs of these two black boxes, we conclude that LSA highly co-relates with HAL and thus there is a justification that LSA and HAL can potentially play a similar role in the area of facilitating automatic query refinement. This paper evaluates LSA in a new application area and contributes an effective way to compare different semantic space models.

Patterns of query reformulation during web searching

Query reformulation is a key user behavior during Web search. Our research goal is to develop predictive models of query reformulation during Web searching. This article reports results from a study in which we automatically classified the query-reformulation patterns for 964,780 Web searching sessions, composed of 1,523,072 queries, to predict the next query reformulation. We employed an n-gram modeling approach to describe the probability of users transitioning from one query-reformulation state to another to predict their next state. We developed first-, second-, third-, and fourth-order models and evaluated each model for accuracy of prediction, coverage of the dataset, and complexity of the possible pattern set. The results show that Reformulation and Assistance account for approximately 45% of all query reformulations; furthermore, the results demonstrate that the first- and second-order models provide the best predictability, between 28 and 40% overall and higher than 70% for some patterns. Implications are that the n-gram approach can be used for improving searching systems and searching assistance.

A task-oriented approach to search engine usability studies

Usability is a multi-dimensional characteristic of a computer system. This paper focuses on usability as a measurement of interaction between the user and the system. The research employs a task-oriented approach to evaluate the usability of a meta search engine. This engine encourages and accepts queries of unlimited size expressed in natural language. A variety of conventional metrics developed by academic and industrial research, including ISO standards,, are applied to the information retrieval process consisting of sequential tasks. Tasks range from formulating (long) queries to interpreting and retaining search results. Results of the evaluation and analysis of the operation log indicate that obtaining advanced search engine results can be accomplished simultaneously with enhancing the usability of the interactive process. In conclusion, we discuss implications for interactive information retrieval system design and directions for future usability research. © 2008 Academy Publisher.

利用构建语义词典的查询自动分类方法

为解决传统的文档分类方法和手工分类方法都不适宜于处理查询分类的问题,提出了一种基于Web的自动构建特定主题的语义词典的方法来分类搜索查询,通过基于主题的Web信息采集和bootstrapping,由某个主题的少量关键词逐步扩充,最终得到该主题的语义词典及词典中每个单词的相对词频.Web中信息的冗余和各主题语义上的差别使各主题的语义词典中单词的种类和数量存在很大差异,这种差异可以用来对用户的搜索查询进行分类.实验结果表明,利用语义词典可以较准确地将用户的查询分类,同时该分类方法基本上不需要人工介入,且可适应搜索查询覆盖面广和实时性强的特点,较好地解决了搜索查询分类的问题.

Query rewriting in information retrieval: automatic context extraction from local user documents to improve query results

The central objective of research in Information Retrieval (IR) is to discover new techniques to retrieve relevant information in order to satisfy an Information Need. The Information Need is satisfied when relevant information can be provided to the user. In IR, relevance is a fundamental concept which has changed over time, from popular to personal, i.e., what was considered relevant before was information for the whole population, but what is considered relevant now is specific information for each user. Hence, there is a need to connect the behavior of the system to the condition of a particular person and his social context; thereby an interdisciplinary sector called Human-Centered Computing was born. For the modern search engine, the information extracted for the individual user is crucial. According to the Personalized Search (PS), two different techniques are necessary to personalize a search: contextualization (interconnected conditions that occur in an activity), and individualization (characteristics that distinguish an individual). This movement of focus to the individual's need undermines the rigid linearity of the classical model overtaken the ``berry picking'' model which explains that the terms change thanks to the informational feedback received from the search activity introducing the concept of evolution of search terms. The development of Information Foraging theory, which observed the correlations between animal foraging and human information foraging, also contributed to this transformation through attempts to optimize the cost-benefit ratio. This thesis arose from the need to satisfy human individuality when searching for information, and it develops a synergistic collaboration between the frontiers of technological innovation and the recent advances in IR. The search method developed exploits what is relevant for the user by changing radically the way in which an Information Need is expressed, because now it is expressed through the generation of the query and its own context. As a matter of fact the method was born under the pretense to improve the quality of search by rewriting the query based on the contexts automatically generated from a local knowledge base. Furthermore, the idea of optimizing each IR system has led to develop it as a middleware of interaction between the user and the IR system. Thereby the system has just two possible actions: rewriting the query, and reordering the result. Equivalent actions to the approach was described from the PS that generally exploits information derived from analysis of user behavior, while the proposed approach exploits knowledge provided by the user. The thesis went further to generate a novel method for an assessment procedure, according to the "Cranfield paradigm", in order to evaluate this type of IR systems. The results achieved are interesting considering both the effectiveness achieved and the innovative approach undertaken together with the several applications inspired using a local knowledge base.

Automatic refinement of constructive solid geometry models

Geometric information relating to most engineering products is available in the form of orthographic drawings or 2D data files. For many recent computer based applications, such as Computer Integrated Manufacturing (CIM), these data are required in the form of a sophisticated model based on Constructive Solid Geometry (CSG) concepts. A recent novel technique in this area transfers 2D engineering drawings directly into a 3D solid model called `the first approximation'. In many cases, however, this does not represent the real object. In this thesis, a new method is proposed and developed to enhance this model. This method uses the notion of expanding an object in terms of other solid objects, which are either primitive or first approximation models. To achieve this goal, in addition to the prepared subroutine to calculate the first approximation model of input data, two other wireframe models are found for extraction of sub-objects. One is the wireframe representation on input, and the other is the wireframe of the first approximation model. A new fast method is developed for the latter special case wireframe, which is named the `first approximation wireframe model'. This method avoids the use of a solid modeller. Detailed descriptions of algorithms and implementation procedures are given. In these techniques utilisation of dashed line information is also considered in improving the model. Different practical examples are given to illustrate the functioning of the program. Finally, a recursive method is employed to automatically modify the output model towards the real object. Some suggestions for further work are made to increase the domain of objects covered, and provide a commercially usable package. It is concluded that the current method promises the production of accurate models for a large class of objects.

Analyzing web multimedia query reformulation behavior

Current multimedia Web search engines still use keywords as the primary means to search. Due to the richness in multimedia contents, general users constantly experience some difficulties in formulating textual queries that are representative enough for their needs. As a result, query reformulation becomes part of an inevitable process in most multimedia searches. Previous Web query formulation studies did not investigate the modification sequences and thus can only report limited findings on the reformulation behavior. In this study, we propose an automatic approach to examine multimedia query reformulation using large-scale transaction logs. The key findings show that search term replacement is the most dominant type of modifications in visual searches but less important in audio searches. Image search users prefer the specified search strategy more than video and audio users. There is also a clear tendency to replace terms with synonyms or associated terms in visual queries. The analysis of the search strategies in different types of multimedia searching provides some insights into user’s searching behavior, which can contribute to the design of future query formulation assistance for keyword-based Web multimedia retrieval systems.

Investigating the performance of automatic new topic identification across multiple datasets 1

Recent studies on automatic new topic identification in Web search engine user sessions demonstrated that neural networks are successful in automatic new topic identification. However most of this work applied their new topic identification algorithms on data logs from a single search engine. In this study, we investigate whether the application of neural networks for automatic new topic identification are more successful on some search engines than others. Sample data logs from the Norwegian search engine FAST (currently owned by Overture) and Excite are used in this study. Findings of this study suggest that query logs with more topic shifts tend to provide more successful results on shift-based performance measures, whereas logs with more topic continuations tend to provide better results on continuation-based performance measures.

Providing query support to leverage BIM for construction

Building information modeling (BIM) is an emerging technology and process that provides rich and intelligent design information models of a facility, enabling enhanced communication, coordination, analysis, and quality control throughout all phases of a building project. Although there are many documented benefits of BIM for construction, identifying essential construction-specific information out of a BIM in an efficient and meaningful way is still a challenging task. This paper presents a framework that combines feature-based modeling and query processing to leverage BIM for construction. The feature-based modeling representation implemented enriches a BIM by representing construction-specific design features relevant to different construction management (CM) functions. The query processing implemented allows for increased flexibility to specify queries and rapidly generate the desired view from a given BIM according to the varied requirements of a specific practitioner or domain. Central to the framework is the formalization of construction domain knowledge in the form of a feature ontology and query specifications. The implementation of our framework enables the automatic extraction and querying of a wide-range of design conditions that are relevant to construction practitioners. The validation studies conducted demonstrate that our approach is significantly more effective than existing solutions. The research described in this paper has the potential to improve the efficiency and effectiveness of decision-making processes in different CM functions.

Optimization of an integrated model for automatic reduction and expansion of long queries

A long query provides more useful hints for searching relevant documents, but it is likely to introduce noise which affects retrieval performance. In order to smooth such adverse effect, it is important to reduce noisy terms, introduce and boost additional relevant terms. This paper presents a comprehensive framework, called Aspect Hidden Markov Model (AHMM), which integrates query reduction and expansion, for retrieval with long queries. It optimizes the probability distribution of query terms by utilizing intra-query term dependencies as well as the relationships between query terms and words observed in relevance feedback documents. Empirical evaluation on three large-scale TREC collections demonstrates that our approach, which is automatic, achieves salient improvements over various strong baselines, and also reaches a comparable performance to a state of the art method based on user’s interactive query term reduction and expansion.