Hybrid XML Retrieval: Combining Information Retrieval and a Native XML Database

Text arrays, created by the online community, contain specific cognitive capabilities. Analyses cover the following: mass media materials, social networks, forums, blogs, political materials, biographies and diaries, scientific publications, belles-letters and other. As practice shows, standard search systems are not always able to find the required data out of this huge volume of the data file. A difficult task for the automated computer text processing is the semantic analysis, which is interpretation of meaning of the text, its content and semantics. Performance of this task requires knowledge of meaning of words and sentences; the way to describe these values formally, and to carry out operations with them, even their storage in computer memory, cause difficulties. That is why in automated text processing computer is not able to search texts of a certain subject, without explicitly specified keywords or phrases, as well as to find texts with the similar meaning, which is quite difficult for the search procedure. Modern information retrieval systems (IRS) are mainly based on key words. The major features for this approach are frequency of word occurrence in document collection, its uniqueness, morphological and syntactic properties. The problem is that the full-text information retrieval systems initially do not imply any semantic connection between the documents and the information they contain, and do not take into account the context and many other issues of importance for semantic interpretation, which makes full-text information retrieval systems unsuitable solution for contextual search. Semantic information retrieval systems should settle the issue of full-text IRS and assist the computer in formal description of semantic meaning of the documents and the data about it. This paper examines possible organization of semantic information-retrieval system based on associations, and uses associative vector spaces as the basic semantic structures.

XML is increasingly used to mark up content in present day information repositories. Over the last decade or so, retrieval from XML document collections has emerged as an area of active research. For the Information Retrieval community, XML retrieval poses a two-fold problem: finding effective techniques to retrieve appropriate or the most useful XML elements in response to a user query; and devising an appropriate evaluation methodology to measure the effectivity of such retrieval techniques. . This study examines both these issues. First, we revisited the pivoted length normalization scheme in the Vector Space Model using standard benchmark collections for XML retrieval. We reduced two parameters used in pivoted length normalization to a single combined parameter and experimentally found its optimum value, which works well at both the element and document levels for XML retrieval. We observed that a substantial number of focused queries used in XML retrieval clearly state, besides the information need, what the user does not want. We demonstrated that this negative information, if not handled properly, degrades retrieval performance. We proposed a solution for automatically removing negative information from XML queries. This led to significant improvements in retrieval results. On the evaluation of XML retrieval, we first studied the sensitivity & robustness of various evaluation metrics and reliability and reusability of the assessment pool that has been used at INEX Ad Hoc track since 2007. Specifically we investigated the behaviour of the metrics when assessments are incomplete, or when query sets are small. We observed that early precision metrics are more error-prone and less stable under both these conditions. Average metric, however, performs comparatively better in this respect. System rankings remain largely unaffected even when assessment effort is substantially (but systematically) reduced. We also found that the INEX collections remain usable when evaluating non-participating systems. For a fixed amount of assessment effort, judging shallow pools for many queries is found to be better than judging deep pools for a smaller set of queries. However, when judging only a random sample of a pool, it is better to completely judge fewer topics than to partially judge many topics. We also proposed a simple and pragmatic approach of creating assessment pool for evaluation of retrieval systems. Instead of using an apriori-fixed pool depth for all topics, the pool is incrementally built and judged interactively on a per query basis. When no new relevant document is found for a reasonably long run of pool-depths, pooling was stopped for the topic. Our proposed approach offers a trade-off between the available effort and required level of performance. Moreover, it is flexible to deep pooling for potential topics in order to ensure better estimate of recall. We demonstrated the effectivity of the technique by substantially reducing the assessment effort without seriously compromising on the reliability of evaluation. The approach provided good results in the evaluation of XML retrieval as well as traditional document retrieval. This doctoral work was done at and submitted to the Indian Statistical Institute, Kolkata, under the supervision of Dr. Mandar Mitra. Dr. Ellen Voorhees and Dr. Tetsuya Sakai served as reviewers; Dr. Soumen Chakrabarti was the examiner at the defence of the thesis. Available online at http://www.isical.ac.in/?mandar/sukomal-thesis.pdf.

In the BlueView project, digital library services are developed and partially implemented based on the architecture of virtual document servers. Using standard tools like full-text databases or information retrieval systems, object-relational database management systems, and replication and caching services, different heterogeneous local document servers have been integrated into one virtual server. Access to heterogeneous local systems can now be performed via a single query interface, integrating features of database query systems and information retrieval or search services. BlueView distributed query processing allows for combining structured queries against meta data with content-based (text retrieval) queries against full-text collections. Legacy systems such as existing preprint servers, search engines, or meta data (catalog) systems can also be integrated. Meta data and full-text documents can be replicated within this distributed architecture. In particular, in the view of members of a certain university, metadata and documents can be replicated to a local document server and integrated under different local user views. Aspects such as terms and conditions, licenses, diverse versions of documents, different formats, and data structures are considered as well. As application scenarios, preprint servers in Mathematics and the ACM SIGMOD Anthology as local document servers have been integrated into a virtual document server.

This tutorial introduces the concept of XML Structural Summaries and describes their role within XML retrieval. It covers the usage of those summaries for Database-style query processing and Information Retrieval-style search tasks in the context of both centralized and distributed environments. Finally, it discusses new retrieval scenarios that can potentially be favorably supported by those summaries.

This is the first year for the Centre for Interactive Systems Research participation of INEX. Based on a newly developed XML indexing and retrieval system on Okapi, we extend Robertson's field-weighted BM25F for document retrieval to element level retrieval function BM25E. In this paper, we introduce this new function and our experimental method in detail, and then show how we tuned weights for our selected fields by using INEX 2004 topics and assessments. Based on the tuned models we submitted our runs for CO.Thorough, CO.FetchBrowse, the methods we propose show real promise. Existing problems and future work are also discussed.

The explosive growth of XML has led to an increasing need for scalable XML retrieval systems. Our XML retrieval system, the SQLGenerator, stores XML of any schema in a fixed schema relational database and supports a full-featured semistructured query language, XML-QL, through optimized translation of its semantics to relational SQL queries. We examine the scalability of this approach with respect to increasing data size. We index four XML collections ranging in size from 500MB to 2GB that were generated using a standard XML generator, XBench. We then compare the execution times of 11 standard XBench queries, covering a wide range of semistructured query features, whose semantics were directly translatable from their original XQuery language to XML-QL. Although it is difficult to estimate the theoretical baseline for scalability of these query features in an RDBMS, many of the queries' runtimes grow linearly with respect to the size of the document collection.

Through the research on the demand of archives utilization, it shows that the full-text retrieval strategy based on the original documents of university archives has some defects, such as bloated index library, slow retrieval speed and difficult to locate page numbers. By extracting abstract information from original documents, this paper expands the information quantity of archives structured data, and constructs a full-text retrieval system based on structured data using Lucene. Through theoretical analysis and simulation comparison, it's shown that the index library is greatly reduced, the retrieval speed is significantly improved, and there's only little change of the recall.

INEX, the evaluation initiative for content-oriented XML retrieval, has since its establishment defined the relevance of an element according to two graded dimensions, exhaustivity and specificity. The former measures how exhaustively an XML element discusses the topic of request, whereas specificity measures how focused the element is on the topic of request. The reason for having two dimensions was to provide a more stable measure of relevance than if assessors were asked to rate the relevance of an element on a single scale. However, obtaining relevance assessments is a costly task. as each document must be assessed for relevance by a human assessor. In XML retrieval this problem is exacerbated as the elements of the document must also be assessed with respect to the exhaustivity and specificity dimensions. A continuous discussion in INEX has been whether such a sophisticated definition of relevance, and in particular the exhaustivity dimension, was needed. This paper attempts to answer this question through extensive statistical tests to compare the conclusions about system performance that could be made under different assessment scenarios.

BackgroundMedical and biological data are commonly with small sample size, missing values, and most importantly, imbalanced class distribution. In this study we propose a particle swarm based hybrid system for remedying the class imbalance problem in medical and biological data mining. This hybrid system combines the particle swarm optimization (PSO) algorithm with multiple classifiers and evaluation metrics for evaluation fusion. Samples from the majority class are ranked using multiple objectives according to their merit in compensating the class imbalance, and then combined with the minority class to form a balanced dataset.ResultsOne important finding of this study is that different classifiers and metrics often provide different evaluation results. Nevertheless, the proposed hybrid system demonstrates consistent improvements over several alternative methods with three different metrics. The sampling results also demonstrate good generalization on different types of classification algorithms, indicating the advantage of information fusion applied in the hybrid system.ConclusionThe experimental results demonstrate that unlike many currently available methods which often perform unevenly with different datasets the proposed hybrid system has a better generalization property which alleviates the method-data dependency problem. From the biological perspective, the system provides indication for further investigation of the highly ranked samples, which may result in the discovery of new conditions or disease subtypes.

With rapid development of Internet technology gradually penetrate to all areas; the number of electronic documents is largely increasing, resulting in contradictions between information overload and people’s desire for knowledge. How to help users take full advantage of the existing full-text retrieval system to get required documents quickly and efficiently from the mass electronic literature has become the objective to the service providers of current digital academic literature. This paper, based on the analysis of relevant users’ interest in behavior modeling technology and main recommended algorithm both domestic and abroad; the current status of full-text retrieval system and characteristics of users, raises a users’ behavior-based personalized full-text retrieval system recommended algorithm. Its main idea is, under the environment of full-text search system, to collect and use users’ implicit behavior data to build their interest model and conduct overall design on the prototype of personalized literature recommendation system supported by the theoretical model.

The demand for psychological counselling has grown significantly in recent years, particularly with the global outbreak of COVID-19, which heightened the need for timely and professional mental health support. Online psychological counselling emerged as the predominant mode of providing services in response to this demand. In this study, we propose the Psy-LLM framework, an AI-based assistive tool leveraging large language models (LLMs) for question answering in psychological consultation settings to ease the demand on mental health professions. Our framework combines pre-trained LLMs with real-world professional questions-and-answers (Q&A) from psychologists and extensively crawled psychological articles. The Psy-LLM framework serves as a front-end tool for healthcare professionals, allowing them to provide immediate responses and mindfulness activities to alleviate patient stress. Additionally, it functions as a screening tool to identify urgent cases requiring further assistance. We evaluated the framework using intrinsic metrics, such as perplexity, and extrinsic evaluation metrics, including human participant assessments of response helpfulness, fluency, relevance, and logic. The results demonstrate the effectiveness of the Psy-LLM framework in generating coherent and relevant answers to psychological questions. This article discusses the potential and limitations of using large language models to enhance mental health support through AI technologies.

In recent years, the use of renewable energy has grown significantly in electricity generation. However, the output of such facilities can be uncertain, affecting their reliability. The forecast of renewable energy production is necessary to guarantee the system’s stability. Several authors have already developed deep learning techniques and hybrid systems to make predictions as accurate as possible. However, the accurate forecasting of renewable energy still is a challenging task. This work proposes a new hybrid system for renewable energy forecasting that combines the traditional linear model (Seasonal Autoregressive Integrated Moving Average—SARIMA) with a state-of-the-art Machine Learning (ML) model, Transformer neural network, using exogenous data. The proposal, named H-Transformer, is compared with other hybrid systems and single ML models, such as Long Short Term Memory (LSTM), Gated Recurrent Unit (GRU), and Recurrent Neural Networks (RNN), using five data sets of wind speed and solar energy. The proposed H-Transformer attained the best result compared to all single models in all datasets and evaluation metrics. Finally, the hybrid H-Transformer obtained the best result in most cases when compared to other hybrid approaches, showing that the proposal can be a useful tool in renewable energy forecasting.

As XML becomes the standard of digital data exchange format we need to manage a lot of XML data effectively. Unlike tables in relational model XML documents are not structural. That makes it difficult to store XML documents as tables in relational model. To solve these problems there have been significant researches in relational database systems. There are two kinds of approaches: 1) One way is to decompose XML documents so that elements of XML match fields of relational tables. 2) The other one stores a whole XML document as a field of relational table. In this paper we adopted the second approach to store XML documents because sometimes it is not easy for us to decompose XML documents and in some cases their element order in documents are very meaningful. We suggest an efficient table schema to store only inverted index as tables to retrieve required data from XML data fields of relational tables and shows SQL translations that correspond to XML full-text retrievals. The functionalities of XML retrieval are based on the W3C XQuery which includes full-text retrievals. In this paper we show the superiority of our method by comparing the performances in terms of a response time and a space to store inverted index. Experiments show our approach uses less space and shows faster response times.

Have the recently introduced outside database, full text retrieval systems helped alleviate editorial page writers' time pressure problems? This study surveyed database retrieval use by 40 writers identified as employees of newspapers that had systems. Results showed 73% of the writers agreed or strongly agreed that lack of time to do adequate research was their biggest problem, but 68% said they seldom or never used the systems. Reasons given for non-use included institutional and personal constraints, and inadequate training.

Audio captioning models play a crucial role in bridging the gap between acoustic in-formation and human language, making digital audio content more accessible and search-able for diverse applications. These systems are increasingly vital in assistive technologies, content management, and surveillance systems where automated understanding of sound-scapes is required. This research has introduced an innovative hybrid captioning method-ology that boosts the capabilities of resource-efficient models without substantially in-creasing their computational footprint. The proposed approach harnesses the advantages of two lightweight audio captioning systems (Whisper-small and CoNeTTE) through a so-phisticated pipeline encompassing multiple stages: initial caption generation, semantic phrase extraction, clustering of related concepts, selection of optimal phrases, and coherent text assembly. This technique enables the creation of richer, more detailed captions by combining the strongest elements from each model's output. Testing on the Clotho dataset revealed significant performance improvements, with the hybrid system surpassing indi-vidual models by substantial margins across all evaluation metrics. On average, the hybrid approach demonstrated enhancements of 28,4% over Whisper-small and 34,3% over CoNeTTE. Particularly impressive gains were observed in METEOR (48,4%) and SPICE (40,4%) metrics, highlighting the hybrid system's superior semantic accuracy and alignment with human-generated descriptions. These findings support our initial hypothesis that dif-ferent architectures capture complementary aspects of audio content, with Whisper-small excelling in precision and CoNeTTE in semantic comprehension. Future research directions include expanding the framework with additional specialized models while refining the semantic clustering with adaptive thresholds. Keywords: audio captioning, large language models, Whisper-small, CoNeTTE.