Free-form Queries Research Articles

Image Retrieval Through Free-Form Query using Intelligent Text Processing

Image Retrieval is the process of retrieving images from the image/multimedia databases. Retrieval of images are carried out with various types of queries, free-form query is a text-query that consists of single or multiple keywords and/or concepts or descriptions of images with or without the inclusion of wild-card characters and/or punctuations. This work aims to handle image retrieval based on free-form text queries. Simple & complex queries of conceptual descriptions of images are explored and an intelligent processing system with free-form queries based on the Bag-of-Words model is modified and built for natural scene images and on Diverse Social Images using the Damerau-Levenshtein edit distance measure. The efficacy of the proposed system is evaluated by testing 1500 free-form text queries and has resulted in a recall accuracy of 91.3% on natural scene images (of Wang/Corel database) and 100% on Diverse Social Images (of DIV400 dataset). These results show that the system proposed has produced satisfactory performance compared to published results such as the harmonic mean of precision and recall (i.e. F1-Score) of 76.70% & 63.32% at retrieval of 20 images etc in reported works.

Free-form CAD model retrieval approach for engineering reuse based on local feature segmentation

For engineering applications, an innovative design can be developed by reusing and modifying existing models with similar features and manufacturing properties, and accurately searching CAD models has become a valuable knowledge acquisition technique in product design. Although there are many retrieval technologies, most methods focus on the global shape of models. In this paper, a CAD model retrieval framework based on local feature segmentation is proposed, offering users a free-form way to choose any subpart as a query from a given model. First, a novel model segmentation method based on the vertex-neighbor extension is proposed to divide a target CAD model into overlapping local features. The chosen subpart with arbitrary boundaries is also successfully described for retrieval by combining local features. Then, a composite descriptor considering both shapes and attribute characteristics is established, which is proved effective for distinguishing local features. Finally, the problem of matching free-form queries to CAD models in the dataset is transformed into descriptor set measurement and is implemented using the bag-of-word algorithm. The proposed model retrieval approach outperforms many existing approaches in matching performance and provides a user-friendly query mode.

Web-Based Information Seeking Behaviors of Low-Literacy Hispanic Survivors of Breast Cancer: Observational Pilot Study.

BackgroundInternet searching is a useful tool for seeking health information and one that can benefit low-literacy populations. However, low-literacy Hispanic survivors of breast cancer do not normally search for health information on the web. For them, the process of searching can be frustrating, as frequent mistakes while typing can result in misleading search results lists. Searches using voice (dictation) are preferred by this population; however, even if an appropriate result list is displayed, low-literacy Hispanic women may be challenged in their ability to fully understand any individual article from that list because of the complexity of the writing.ObjectiveThis observational study aims to explore and describe web-based search behaviors of Hispanic survivors of breast cancer by themselves and with their caregivers, as well as to describe the challenges they face when processing health information on the web.MethodsWe recruited 7 Hispanic female survivors of breast cancer. They had the option to bring a caregiver. Of the 7 women, 3 (43%) did, totaling 10 women. We administered the Health LiTT health literacy test, a demographic survey, and a breast cancer knowledge assessment. Next, we trained the participants to search on the web with either a keyboard or via voice. Then, they had to find information about 3 guided queries and 1 free-form query related to breast cancer. Participants were allowed to search in English or in Spanish. We video and audio recorded the computer activity of all participants and analyzed it.ResultsWe found web articles to be written for a grade level of 11.33 in English and 7.15 in Spanish. We also found that most participants preferred searching using voice but struggled with this modality. Pausing while searching via voice resulted in incomplete search queries, as it confused the search engine. At other times, background noises were detected and included in the search. We also found that participants formulated overly general queries to broaden the results list hoping to find more specific information. In addition, several participants considered their queries satisfied based on information from the snippets on the result lists alone. Finally, participants who spent more time reviewing articles scored higher on the health literacy test.ConclusionsDespite the problems of searching using speech, we found a preference for this modality, which suggests a need to avoid potential errors that could appear in written queries. We also found the use of general questions to increase the chances of answers to more specific concerns. Understanding search behaviors and information evaluation strategies for low-literacy Hispanic women survivors of breast cancer is fundamental to designing useful search interfaces that yield relevant and reliable information on the web.

KrillDB: A de novo transcriptome database for the Antarctic krill (Euphausia superba).

Antarctic krill (Euphausia superba) is a key species in the Southern Ocean with an estimated biomass between 100 and 500 million tonnes. Changes in krill population viability would have catastrophic effect on the Antarctic ecosystem. One looming threat due to elevated levels of anthropogenic atmospheric carbon dioxide (CO2) is ocean acidification (lowering of sea water pH by CO2 dissolving into the oceans). The genetics of Antarctic krill has long been of scientific interest for both for the analysis of population structure and analysis of functional genetics. However, the genetic resources available for the species are relatively modest. We have developed the most advanced genetic database on Euphausia superba, KrillDB, which includes comprehensive data sets of former and present transcriptome projects. In particular, we have built a de novo transcriptome assembly using more than 360 million Illumina sequence reads generated from larval krill including individuals subjected to different CO2 levels. The database gives access to: 1) the full list of assembled genes and transcripts; 2) their level of similarity to transcripts and proteins from other species; 3) the predicted protein domains contained within each transcript; 4) their predicted GO terms; 5) the level of expression of each transcript in the different larval stages and CO2 treatments. All references to external entities (sequences, domains, GO terms) are equipped with a link to the appropriate source database. Moreover, the software implements a full-text search engine that makes it possible to submit free-form queries. KrillDB represents the first large-scale attempt at classifying and annotating the full krill transcriptome. For this reason, we believe it will constitute a cornerstone of future approaches devoted to physiological and molecular study of this key species in the Southern Ocean food web.

Synthesizing Java expressions from free-form queries

We present a new code assistance tool for integrated development environments. Our system accepts as input free-form queries containing a mixture of English and Java, and produces Java code expressions that take the query into account and respect syntax, types, and scoping rules of Java, as well as statistical usage patterns. In contrast to solutions based on code search, the results returned by our tool need not directly correspond to any previously seen code fragment. As part of our system we have constructed a probabilistic context free grammar for Java constructs and library invocations, as well as an algorithm that uses a customized natural language processing tool chain to extract information from free-form text queries. We present the results on a number of examples showing that our technique (1) often produces the expected code fragments, (2) tolerates much of the flexibility of natural language, and (3) can repair incorrect Java expressions that use, for example, the wrong syntax or missing arguments.

Free-Form Query for Cell Phones

To provide a wide range of queries to database query systems for small mobile devices, such as the PDAs and cell phones, is a challenge. Currently, due to the physical and resource limitations of these devices, most reported database querying systems developed for them are only offering a small set of pre-determined queries for users to possibly pose. We believe that by allowing free-form queries to be entered on the cell phones will be one way of supporting a wider scope of queries on these devices. Hence, this paper presents the free-form query language that can be used to issue free-form queries and the method used in translating these queries to their equivalent SQL statements.

Semantic retrieval and ranking of Semantic Web documents using free-form queries

Recent advances in the Semantic Web research community actuated the experimentation with a variety of approaches concerning the retrieval of Semantic Web Documents (SWDs). Most approaches require that queries are formed in a structured and formal way. Given the inability of the majority of web users to express formal queries, this paper proposes an approach to SWDs' retrieval, aiming to support users to place queries, requiring no knowledge and skills for expressing these queries in a formal language. The paper discusses specific issues that are considered towards the retrieval of SWDs using free-form queries and presents an evaluated two-step approach.

CLASCN: Candidate Network Selection for Efficient Top-k Keyword Queries over Databases

Keyword Search Over Relational Databases (KSORD) enables casual or Web users easily access databases through free-form keyword queries. Improving the performance of KSORD systems is a critical issue in this area. In this paper, a new approach CLASCN (Classification, Learning And Selection of Candidate Network) is developed to efficiently perform top-k keyword queries in schema-graph-based online KSORD systems. In this approach, the Candidate Networks (CNs) from trained keyword queries or executed user queries are classified and stored in the databases, and top-k results from the CNs are learned for constructing CN Language Models (CNLMs). The CNLMs are used to compute the similarity scores between a new user query and the CNs from the query. The CNs with relatively large similarity score, which are the most promising ones to produce top-k results, will be selected and performed. Currently, CLASCN is only applicable for past queries and New All-keyword-Used (NAU) queries which are frequently submitted queries. Extensive experiments also show the efficiency and effectiveness of our CLASCN approach.

Interest-based personalized search

Web search engines typically provide search results without considering user interests or context. We propose a personalized search approach that can easily extend a conventional search engine on the client side. Our mapping framework automatically maps a set of known user interests onto a group of categories in the Open Directory Project (ODP) and takes advantage of manually edited data available in ODP for training text classifiers that correspond to, and therefore categorize and personalize search results according to user interests. In two sets of controlled experiments, we compare our personalized categorization system (PCAT) with a list interface system (LIST) that mimics a typical search engine and with a nonpersonalized categorization system (CAT). In both experiments, we analyze system performances on the basis of the type of task and query length. We find that PCAT is preferable to LIST for information gathering types of tasks and for searches with short queries, and PCAT outperforms CAT in both information gathering and finding types of tasks, and for searches associated with free-form queries. From the subjects' answers to a questionnaire, we find that PCAT is perceived as a system that can find relevant Web pages quicker and easier than LIST and CAT.