Search results for: content based retrieval

Authors: Rui Yin, Haojie Wang, Xun Li

Abstract:

Recently, mainstream dense retrieval methods have obtained state-of-the-art results on some datasets and tasks. However, they require large amounts of training data, which is not available in most domains. The severe performance degradation of dense retrievers on new data domains has limited the use of dense retrieval methods to only a few domains with large training datasets. In this paper, we propose an unsupervised domain-adaptive approach based on query generation. First, a generative model is used to generate relevant queries for each passage in the target corpus, and then, the generated queries are used for mining negative passages. Finally, the query-passage pairs are labeled with a cross-encoder and used to train a domain-adapted dense retriever. We also explore contrastive learning as a method for training domain-adapted dense retrievers and show that it leads to strong performance in various retrieval settings. Experiments show that our approach is more robust than previous methods in target domains that require less unlabeled data.

Keywords: dense retrieval, query generation, contrastive learning, unsupervised training

Procedia PDF Downloads 105

Authors: Simone B. K. Aires, Cinthia O. de A. Freitas, Luiz E. S. Oliveira

Abstract:

This paper contributes to the CBIR systems applied to trademark retrieval. The proposed model includes aspects from visual perception of the shapes, by means of feature extractor associated to a non-symmetrical perceptual zoning mechanism based on the Principles of Gestalt. Thus, the feature set were performed using Scale Invariant Feature Transform (SIFT). We carried out experiments using four different zonings strategies (Z = 4, 5H, 5V, 7) for matching and retrieval tasks. Our proposal method achieved the normalized recall (Rn) equal to 0.84. Experiments show that the non-symmetrical zoning could be considered as a tool to build more reliable trademark retrieval systems.

Keywords: CBIR, Gestalt, matching, non-symmetrical zoning, SIFT

Procedia PDF Downloads 314

Authors: B. J. Sandesh, Saurabha Jirgi, S. Vidya, Prakash Eljer, Gowri Srinivasa

Abstract:

In this paper, we propose a framework to help users to search and retrieve the portions in the lecture video of their interest. This is achieved by temporally segmenting and indexing the lecture video using the topic keywords. We use transcribed text from the video and documents relevant to the video topic extracted from the web for this purpose. The keywords for indexing are found by applying the non-negative matrix factorization (NMF) topic modeling techniques on the web documents. Our proposed technique first creates indices on the transcribed documents using the topic keywords, and these are mapped to the video to find the start and end time of the portions of the video for a particular topic. This time information is stored in the index table along with the topic keyword which is used to retrieve the specific portions of the video for the query provided by the users.

Keywords: video indexing and retrieval, lecture videos, content based video search, multimodal indexing

Procedia PDF Downloads 251

Authors: S. Tehsin, S. Kausar

Abstract:

The ultimate aim of machine intelligence is to explore and materialize the human capabilities, one of which is the ability to detect various text objects within one or more images displayed on any canvas including prints, videos or electronic displays. Multimedia data has increased rapidly in past years. Textual information present in multimedia contains important information about the image/video content. However, it needs to technologically testify the commonly used human intelligence of detecting and differentiating the text within an image, for computers. Hence in this paper feature set based on anatomical study of human text detection system is proposed. Subsequent examination bears testimony to the fact that the features extracted proved instrumental to text detection.

Keywords: biologically inspired vision, content based retrieval, document analysis, text extraction

Procedia PDF Downloads 446

Authors: Khaled M. Alhawiti

Abstract:

This paper aims to analyze the role of natural language processing (NLP). The paper will discuss the role in the context of automated data retrieval, automated question answer, and text structuring. NLP techniques are gaining wider acceptance in real life applications and industrial concerns. There are various complexities involved in processing the text of natural language that could satisfy the need of decision makers. This paper begins with the description of the qualities of NLP practices. The paper then focuses on the challenges in natural language processing. The paper also discusses major techniques of NLP. The last section describes opportunities and challenges for future research.

Keywords: data retrieval, information retrieval, natural language processing, text structuring

Procedia PDF Downloads 341

Authors: Aman Berhe, Camille Guinaudeau, Claude Barras

Abstract:

In order to facilitate information seeking in large collections of multimedia documents with long and progressive content (such as broadcast news or TV series), one can extract the semantic links that exist between semantically coherent parts of documents, i.e., scenes. The links can then create a coherent collection of scenes from which it is easier to perform content analysis, topic extraction, or information retrieval. In this paper, we focus on TV series structuring and propose two approaches for scene linking at different levels of granularity (episode and season): a fuzzy online clustering technique and a graph-based community detection algorithm. When evaluated on the two first seasons of the TV series Game of Thrones, we found that the fuzzy online clustering approach performed better compared to graph-based community detection at the episode level, while graph-based approaches show better performance at the season level.

Keywords: multimedia collection structuring, progressive content, scene linking, fuzzy clustering, community detection

Procedia PDF Downloads 101

Authors: Jian Qu, Akira Shimazu

Abstract:

OOV (Out Of Vocabulary) terms are terms that cannot be found in many dictionaries. Although it is possible to translate such OOV terms, the translations do not provide any real information for a user. We present an OOV term definition extraction method by using information available from the Internet. We use features such as occurrence of the synonyms and location distances. We apply machine learning method to find the correct definitions for OOV terms. We tested our method on both biomedical type and name type OOV terms, our work outperforms existing work with an accuracy of 86.5%.

Keywords: information retrieval, definition retrieval, OOV (out of vocabulary), biomedical information retrieval

Procedia PDF Downloads 496

Authors: Ahmadu Maidorawa, Idrissa Djibo, Muhammad Tella

Abstract:

This paper presents a method for detecting flow chart and figure plagiarism based on shape of image processing and multimedia retrieval. The method managed to retrieve flowcharts with ranked similarity according to different matching sets. Plagiarism detection is well known phenomenon in the academic arena. Copying other people is considered as serious offense that needs to be checked. There are many plagiarism detection systems such as turn-it-in that has been developed to provide these checks. Most, if not all, discard the figures and charts before checking for plagiarism. Discarding the figures and charts result in look holes that people can take advantage. That means people can plagiarize figures and charts easily without the current plagiarism systems detecting it. There are very few papers which talks about flowcharts plagiarism detection. Therefore, there is a need to develop a system that will detect plagiarism in figures and charts.

Keywords: flowchart, multimedia retrieval, figures similarity, image comparison, figure retrieval

Procedia PDF Downloads 467

Authors: Kehinde Agbele, Longe Olumide, Daniel Ekong, Dele Seluwa, Akintoye Onamade

Abstract:

One major problem of most existing information retrieval systems (IRS) is that they provide even access and retrieval results to individual users specially based on the query terms user issued to the system. When using IRS, users often present search queries made of ad-hoc keywords. It is then up to IRS to obtain a precise representation of user’s information need, and the context of the information. In effect, the volume and range of the Internet documents is growing exponentially and consequently causes difficulties for a user to obtain information that precisely matches the user interest. Diverse combination techniques are used to achieve the specific goal. This is due, firstly, to the fact that users often do not present queries to IRS that optimally represent the information they want, and secondly, the measure of a document's relevance is highly subjective between diverse users. In this paper, we address the problem by investigating the optimization of IRS to individual information needs in order of relevance. The paper addressed the development of algorithms that optimize the ranking of documents retrieved from IRS. This paper addresses this problem with a two-fold approach in order to retrieve domain-specific documents. Firstly, the design of context of information. The context of a query determines retrieved information relevance using personalization and context-awareness. Thus, executing the same query in diverse contexts often leads to diverse result rankings based on the user preferences. Secondly, the relevant context aspects should be incorporated in a way that supports the knowledge domain representing users’ interests. In this paper, the use of evolutionary algorithms is incorporated to improve the effectiveness of IRS. A context-based information retrieval system that learns individual needs from user-provided relevance feedback is developed whose retrieval effectiveness is evaluated using precision and recall metrics. The results demonstrate how to use attributes from user interaction behavior to improve the IR effectiveness.

Keywords: context, document relevance, information retrieval, personalization, user search behaviors

Procedia PDF Downloads 464

Authors: Janya Sainui

Abstract:

As a rapid growth of digital videos and data communications, video summarization that provides a shorter version of the video for fast video browsing and retrieval is necessary. Key frame extraction is one of the mechanisms to generate video summary. In general, the extracted key frames should both represent the entire video content and contain minimum redundancy. However, most of the existing approaches heuristically select key frames; hence, the selected key frames may not be the most different frames and/or not cover the entire content of a video. In this paper, we propose a method of video summarization which provides the reasonable objective functions for selecting key frames. In particular, we apply a statistical dependency measure called quadratic mutual informaion as our objective functions for maximizing the coverage of the entire video content as well as minimizing the redundancy among selected key frames. The proposed key frame extraction algorithm finds key frames as an optimization problem. Through experiments, we demonstrate the success of the proposed video summarization approach that produces video summary with better coverage of the entire video content while less redundancy among key frames comparing to the state-of-the-art approaches.

Keywords: video summarization, key frame extraction, dependency measure, quadratic mutual information

Procedia PDF Downloads 267

Authors: Saad M. Darwish, Mohamed A. El-Iskandarani, Guitar M. Shawkat

Abstract:

Nowadays, the amount of available multimedia data is continuously on the rise. The need to find a required image for an ordinary user is a challenging task. Content based image retrieval (CBIR) computes relevance based on the visual similarity of low-level image features such as color, textures, etc. However, there is a gap between low-level visual features and semantic meanings required by applications. The typical method of bridging the semantic gap is through the automatic image annotation (AIA) that extracts semantic features using machine learning techniques. In this paper, a multi-label image annotation system guided by Firefly and Bayesian method is proposed. Firstly, images are segmented using the maximum variance intra cluster and Firefly algorithm, which is a swarm-based approach with high convergence speed, less computation rate and search for the optimal multiple threshold. Feature extraction techniques based on color features and region properties are applied to obtain the representative features. After that, the images are annotated using translation model based on the Net Bayes system, which is efficient for multi-label learning with high precision and less complexity. Experiments are performed using Corel Database. The results show that the proposed system is better than traditional ones for automatic image annotation and retrieval.

Keywords: feature extraction, feature selection, image annotation, classification

Procedia PDF Downloads 586

Authors: Nihad Karim Chowdhury, Mohammad Sanaullah Chowdhury, Muhammed Jamshed Alam Patwary, Rubel Biswas

Abstract:

In content-based 3D shape retrieval system, achieving high search performance has become an important research problem. A challenging aspect of this problem is to find an effective shape descriptor which can discriminate similar shapes adequately. To address this problem, we propose a new shape descriptor for 3D shape models by combining multi-resolution with multi-block center-symmetric local binary pattern operator. Given an arbitrary 3D shape, we first apply pose normalization, and generate a set of multi-viewed 2D rendered images. Second, we apply Gaussian multi-resolution filter to generate several levels of images from each of 2D rendered image. Then, overlapped sub-images are computed for each image level of a multi-resolution image. Our unique multi-block CS-LBP comes next. It allows the center to be composed of m-by-n rectangular pixels, instead of a single pixel. This process is repeated for all the 2D rendered images, derived from both ‘depth-buffer’ and ‘silhouette’ rendering. Finally, we concatenate all the features vectors into one dimensional histogram as our proposed 3D shape descriptor. Through several experiments, we demonstrate that our proposed 3D shape descriptor outperform the previous methods by using a benchmark dataset.

Keywords: 3D shape retrieval, 3D shape descriptor, CS-LBP, overlapped sub-images

Procedia PDF Downloads 448

Authors: Ben G. Weber, Michael Mateas

Abstract:

We present a case-based reasoning technique for selecting build orders in a real-time strategy game. The case retrieval process generalizes features of the game state and selects cases using domain-specific recall methods, which perform exact matching on a subset of the case features. We demonstrate the performance of the technique by implementing it as a component of the integrated agent framework of McCoy and Mateas. Our results demonstrate that the technique outperforms nearest-neighbor retrieval when imperfect information is enforced in a real-time strategy game.

Keywords: case based reasoning, real time strategy systems, requirements elicitation, requirement analyst, artificial intelligence

Procedia PDF Downloads 442

Authors: Piedad Garrido, Fernando Repulles, Andy Bloor, Julio A. Sanguesa, Jesus Gallardo, Vicente Torres, Jesus Tramullas

Abstract:

With the emergence and development of Information and Communications Technologies (ICTs), Higher Education is experiencing rapid changes, not only in its teaching strategies but also in student’s learning skills. However, we have noticed that students often have difficulty when seeking innovative, useful, and interesting learning resources for their work. This is due to the lack of supervision in the selection of good query tools. This paper presents AINA, an Information Retrieval (IR) computer system aimed at providing motivating and stimulating content to both students and teachers working on different areas and at different educational levels. In particular, our proposal consists of an open virtual resource environment oriented to the vast universe of Disney comics and cartoons. Our test suite includes Disney’s long and shorts films, and we have performed some activities based on the Just In Time Teaching (JiTT) methodology. More specifically, it has been tested by groups of university and secondary school students.

Keywords: information retrieval, animation, educational resources, JiTT

Procedia PDF Downloads 348

Authors: June-Jei Kuo, Yi-Chuan Hsieh

Abstract:

Because of the rapid growth of information technology, more and more libraries introduce the new information retrieval systems to enhance the users’ experience, improve the retrieval efficiency, and increase the applicability of the library resources. Nevertheless, few of them are discussed the usability from the users’ aspect. The aims of this study are to understand that the scenario of the information retrieval system utilization, and to know why users are willing to continuously use the web-scale discovery system to improve the web-scale discovery system and promote their use of university libraries. Besides of questionnaires, observations and interviews, this study employs both Information System Success Model introduced by DeLone and McLean in 2003 and the flow theory to evaluate the system quality, information quality, service quality, use, user satisfaction, flow, and continuing to use web-scale discovery system of students from National Chung Hsing University. Then, the results are analyzed through descriptive statistics and structural equation modeling using AMOS. The results reveal that in web-scale discovery system, the user’s evaluation of system quality, information quality, and service quality is positively related to the use and satisfaction; however, the service quality only affects user satisfaction. User satisfaction and the flow show a significant impact on continuing to use. Moreover, user satisfaction has a significant impact on user flow. According to the results of this study, to maintain the stability of the information retrieval system, to improve the information content quality, and to enhance the relationship between subject librarians and students are recommended for the academic libraries. Meanwhile, to improve the system user interface, to minimize layer from system-level, to strengthen the data accuracy and relevance, to modify the sorting criteria of the data, and to support the auto-correct function are required for system provider. Finally, to establish better communication with librariana commended for all users.

Keywords: web-scale discovery system, discovery system, information system success model, flow theory, academic library

Procedia PDF Downloads 104

Authors: Mei-Yi Wu, Shang-Ming Huang

Abstract:

The online shoppers nowadays often search the product information on the Internet using some keywords of products. To use this kind of information searching model, shoppers should have a preliminary understanding about their interesting products and choose the correct keywords. However, if the products are first contact (for example, the worn clothes or backpack of passengers which you do not have any idea about the brands), these products cannot be retrieved due to insufficient information. In this paper, we discuss and study the applications in E-commerce using image retrieval and text mining techniques. We design a reasonable E-commerce application system containing three layers in the architecture to provide users product information. The system can automatically search and retrieval similar images and corresponding web pages on Internet according to the target pictures which taken by users. Then text mining techniques are applied to extract important keywords from these retrieval web pages and search the prices on different online shopping stores with these keywords using a web crawler. Finally, the users can obtain the product information including photos and prices of their favorite products. The experiments shows the efficiency of proposed system.

Keywords: mobile image retrieval, text mining, product information service system, online marketing

Procedia PDF Downloads 360

Authors: Benhamouda Sara, Guezouli Larbi

Abstract:

Nowadays, the dissemination of information touches the distributed world, where selecting the relevant servers to a user request is an important problem in distributed information retrieval. During the last decade, several research studies on this issue have been launched to find optimal solutions and many approaches of collection selection have been proposed. In this paper, we propose a new collection selection approach that takes into consideration the number of documents in a collection that contains terms of the query and the weights of those terms in these documents. We tested our method and our studies show that this technique can compete with other state-of-the-art algorithms that we choose to test the performance of our approach.

Keywords: distributed information retrieval, relevance, server selection, collection selection

Procedia PDF Downloads 314

Authors: Faiza Hussain, Usman Qamar

Abstract:

Synonym-based searching is recognized to be a complicated problem as text mining from unstructured data of web is challenging. Finding useful information which matches user need from bulk of web pages is a cumbersome task. In this paper, a novel and practical synonym retrieval technique is proposed for addressing this problem. For replacement of semantics, user intent is taken into consideration to realize the technique. Parts-of-Speech tagging is applied for pattern generation of the query and a thesaurus for this experiment was formed and used. Comparison with Non-Context Based Searching, Context Based searching proved to be a more efficient approach while dealing with linguistic semantics. This approach is very beneficial in doing intent based searching. Finally, results and future dimensions are presented.

Keywords: natural language processing, text mining, information retrieval, parts-of-speech tagging, grammar, semantics

Procedia PDF Downloads 308

Authors: Amel Hannech, Mehdi Adda, Hamid Mcheick

Abstract:

In computer science, the purpose of finding useful information is still one of the most active and important research topics. The most popular application of information retrieval (IR) are Search Engines, they meet users' specific needs and aim to locate the effective information in the web. However, these search engines have some limitations related to the relevancy of the results and the ease to explore those results. In this context, we proposed in previous works a Multi-Space Search Engine model that is based on a multidimensional interpretation universe. In the present paper, we integrate an additional dimension that allows to offer users new research experiences. The added component is based on creating user profiles and calculating the similarity between them that then allow the use of collaborative filtering in retrieving search results. To evaluate the effectiveness of the proposed model, a prototype is developed. The experiments showed that the additional dimension has improved the relevancy of results by predicting the interesting items of users based on their experiences and the experiences of other similar users. The offered personalization service allows users to approve the pertinent items, which allows to enrich their profiles and further improve research.

Keywords: information retrieval, v-facets, user behavior analysis, user profiles, topical ontology, association rules, data personalization

Procedia PDF Downloads 264

Authors: El Asnaoui Khalid, Aksasse Brahim, Ouanan Mohammed

Abstract:

In this paper, we are interested in the problem of finding similar images in a large database. For this purpose we propose a new algorithm based on a combination of the 2-D histogram intersection in the HSV space and statistical moments. The proposed histogram is based on a 3x3 window and not only on the intensity of the pixel. This approach can overcome the drawback of the conventional 1-D histogram which is ignoring the spatial distribution of pixels in the image, while the statistical moments are used to escape the effects of the discretisation of the color space which is intrinsic to the use of histograms. We compare the performance of our new algorithm to various methods of the state of the art and we show that it has several advantages. It is fast, consumes little memory and requires no learning. To validate our results, we apply this algorithm to search for similar images in different image databases.

Keywords: 2-D histogram, statistical moments, indexing, similarity distance, histograms intersection

Procedia PDF Downloads 457

Authors: Ma'amun Muhammed

Abstract:

The ability of smartphones in enhancing communication, providing access to business and serving as a pool for information retrieval has a far reaching and potentially beneficial impacts on enhancing teaching in higher institutions in the developing countries like Nigeria. Nigeria as one of the fast growing economies in Africa, whose citizens patronize smartphones can utilize this opportunity by inculcating the culture of using smartphones not only for communication, business transaction, banking etc. but also for enhancing teaching in the higher institutions. Smartphones have become part and parcel of our lives, particularly among young people. The primary objective of this paper is to ascertain the use of smartphones in enhancing teaching in Nigeria’s higher institutions, to achieve this, content analysis was used thoroughly. This paper examines the opportunities offered by smartphones to the students of higher institutions of learning, the challenges being faced by lecturers of these institutions in classrooms. Lastly, it offers solution on how some of these critical challenges will be overcame, so as to utilize the technology of these devices.

Keywords: communication, information retrieval, mobile phone, smartphones teaching

Procedia PDF Downloads 425

Authors: Wen-Jye Shyr, Chun-Yuan Chang, Bo-Lin Wei, Chia-Ming Lin

Abstract:

The task of creating an augmented reality technology was described in this study to give operators a user interface that might be a part of an automated storage and retrieval system. Its objective was to give graduate engineering and technology students a system of tools with which to experiment with the creation of augmented reality technologies. To collect and analyze data for maintenance applications, the students used augmented reality technology. Our findings support the evolution of artificial intelligence towards Industry 4.0 practices and the planned Industry 4.0 research stream. Important first insights into the study's effects on student learning were presented.

Keywords: augmented reality, storage and retrieval system, user interface, programmable logic controller

Procedia PDF Downloads 89

Authors: Ahmad FAROOQ, Xinfeng Zhang, Fahad Sabah, Raheem Sarwar

Abstract:

In Traditional Chinese Medicine, tongue diagnosis is a vital inspection tool (TCM). In this study, we explore the potential of machine learning in tongue diagnosis. It begins with the cataloguing of the various classifications and characteristics of the human tongue. We infer 24 kinds of tongues from the material and coating of the tongue, and we identify 21 attributes of the tongue. The next step is to apply machine learning methods to the tongue dataset. We use the Weka machine learning platform to conduct the experiment for performance analysis. The 457 instances of the tongue dataset are used to test the performance of five different machine learning methods, including SVM, Random Forests, Decision Trees, and Naive Bayes. Based on accuracy and Area under the ROC Curve, the Support Vector Machine algorithm was shown to be the most effective for tongue diagnosis (AUC).

Keywords: medical imaging, image retrieval, machine learning, tongue

Procedia PDF Downloads 82

Authors: Liu Linxin

Abstract:

As system complexity increases, log parsing and anomaly detection become more and more important in ensuring system stability. However, traditional methods often face the problems of insufficient adaptability and decreasing accuracy when dealing with rapidly changing log contents and unknown domains. To this end, this paper proposes an approach LogRAG, which combines RAG (Retrieval Augmented Generation) technology with Prompt Engineering for Large Language Models, applied to log analysis tasks to achieve dynamic parsing of logs and intelligent anomaly detection. By combining real-time information retrieval and prompt optimisation, this study significantly improves the adaptive capability of log analysis and the interpretability of results. Experimental results show that the method performs well on several public datasets, especially in the absence of training data, and significantly outperforms traditional methods. This paper provides a technical path for log parsing and anomaly detection, demonstrating significant theoretical value and application potential.

Keywords: log parsing, anomaly detection, retrieval-augmented generation, prompt engineering, LLMs

Procedia PDF Downloads 31

Authors: Ahmed Fradi

Abstract:

Nowadays, recent technological advances in the acquisition, modeling, and processing of three-dimensional (3D) objects data lead to the creation of models stored in huge databases, which are used in various domains such as computer vision, augmented reality, game industry, medicine, CAD (Computer-aided design), 3D printing etc. On the other hand, the industry is currently benefiting from powerful modeling tools enabling designers to easily and quickly produce 3D models. The great ease of acquisition and modeling of 3D objects make possible to create large 3D models databases, then, it becomes difficult to navigate them. Therefore, the indexing of 3D objects appears as a necessary and promising solution to manage this type of data, to extract model information, retrieve an existing model or calculate similarity between 3D objects. The objective of the proposed research is to develop a framework allowing easy and fast access to 3D objects in a CAD models database with specific indexing algorithm to find objects similar to a reference model. Our main objectives are to study existing methods of similarity calculation of 3D objects (essentially shape-based methods) by specifying the characteristics of each method as well as the difference between them, and then we will propose a new approach for indexing and comparing 3D models, which is suitable for our case study and which is based on some previously studied methods. Our proposed approach is finally illustrated by an implementation, and evaluated in a professional context.

Keywords: CAD, 3D object retrieval, shape based retrieval, similarity calculation

Procedia PDF Downloads 263

Authors: Aagesson, Ekstrand, Persson, Sallander

Abstract:

A description of how a team of librarians at Linnaeus University Library in Sweden utilizes a pedagogical approach to deliver engaging digital workshops on information retrieval. The team consists of four librarians supporting three different faculties. The paper discusses the challenges faced in engaging students who may perceive information retrieval as a boring and difficult subject. The paper emphasizes the importance of motivation, inclusivity, constructive feedback, and collaborative learning in enhancing student engagement. By employing a two-librarian teaching model, maintaining a lighthearted approach, and relating information retrieval to everyday experiences, the team aimed to create an enjoyable and meaningful learning experience. The authors describe their approach to increase student engagement and learning outcomes through a three-phase workshop structure: before, during, and after the workshops. The "flipped classroom" method was used, where students were provided with pre-workshop materials, including a short film on information search and encouraged to reflect on the topic using a digital collaboration tool. During the workshops, interactive elements such as quizzes, live demonstrations, and practical training were incorporated, along with opportunities for students to ask questions and provide feedback. The paper concludes by highlighting the benefits of the flipped classroom approach and the extended learning opportunities provided by the before and after workshop phases. The authors believe that their approach offers a sustainable alternative for enhancing information retrieval knowledge among students at Linnaeus University.

Keywords: digital workshop, flipped classroom, information retrieval, interactivity, LIS practitioner, student engagement

Procedia PDF Downloads 67

Authors: Ganfeng Yu, Yuefeng Ma, Shanliang Yang

Abstract:

The word discovery is a key problem in text information retrieval technology. Methods in new word discovery tend to be closely related to words because they generally obtain new word results by analyzing words. With the popularity of social networks, individual netizens and online self-media have generated various network texts for the convenience of online life, including network words that are far from standard Chinese expression. How detect network words is one of the important goals in the field of text information retrieval today. In this paper, we integrate the word embedding model and clustering methods to propose a network word discovery framework based on sentence semantic similarity (S³-NWD) to detect network words effectively from the corpus. This framework constructs sentence semantic vectors through a distributed representation model, uses the similarity of sentence semantic vectors to determine the semantic relationship between sentences, and finally realizes network word discovery by the meaning of semantic replacement between sentences. The experiment verifies that the framework not only completes the rapid discovery of network words but also realizes the standard word meaning of the discovery of network words, which reflects the effectiveness of our work.

Keywords: text information retrieval, natural language processing, new word discovery, information extraction

Procedia PDF Downloads 100

Authors: Bruno T. Gomes, José A. Menezes, Giordano Cabral

Abstract:

With the popularity of smartphones, mobile apps emerge to meet the diverse needs, however the resources at the disposal are limited, either by the hardware, due to the low computing power, or the software, that does not have the same robustness of desktop environment. For example, in automatic audio classification (AC) tasks, musical information retrieval (MIR) subarea, is required a fast processing and a good success rate. However the mobile platform has limited computing power and the best AC tools are only available for desktop. To solve these problems the fast classifier suits, to mobile environments, the most widespread MIR technologies, seeking a balance in terms of speed and robustness. At the end we found that it is possible to enjoy the best of MIR for mobile environments. This paper presents the results obtained and the difficulties encountered.

Keywords: audio classification, audio extraction, environment mobile, musical information retrieval

Procedia PDF Downloads 547

Authors: Sean W. T. Bayly, Daniel Glover, Don Horrell, Simon Horrocks, Barnes Callum, Stuart Gibson, Mac Misuira

Abstract:

We assess suitability of recent, ∼7B parameter, instruction-tuned Language Models for Generative Named Entity Recognition (GNER). Alongside Retrieval Augmented Generation (RAG), and supported by task-specific prompting, our proposed Multi-Level Information Retrieval method achieves notable improvements over finetuned entity-level and sentence-level methods. We conclude that language models directed toward this task are highly capable when distinguishing between positive classes (precision). However, smaller models seem to struggle to find all entities (recall). Poorly defined classes such as ”Miscellaneous” exhibit substantial declines in performance, likely due to the ambiguity it introduces to the prompt. This is partially resolved through a self-verification method using engineered prompts containing knowledge of the stricter class definitions, particularly in areas where their boundaries are in danger of overlapping, such as the conflation between the location ”Britain” and the nationality ”British”. Finally, we explore correlations between model performance on the GNER task with performance on relevant academic benchmarks.

Keywords: generative named entity recognition, information retrieval, lightweight artificial intelligence, prompt engineering, personal information identification, retrieval augmented generation, self verification

Procedia PDF Downloads 49

Authors: Liu Lin Xin

Abstract:

With the increasing complexity of systems, log parsing and anomaly detection have become crucial for maintaining system stability. However, traditional methods often struggle with adaptability and accuracy, especially when dealing with rapidly evolving log content and unfamiliar domains. To address these challenges, this paper proposes approach that integrates Retrieval Augmented Generation (RAG) technology with Prompt Engineering for Large Language Models, applied specifically in LogPrompt. This approach enables dynamic log parsing and intelligent anomaly detection by combining real-time information retrieval with prompt optimization. The proposed method significantly enhances the adaptability of log analysis and improves the interpretability of results. Experimental results on several public datasets demonstrate the method's superior performance, particularly in scenarios lacking training data, where it significantly outperforms traditional methods. This paper introduces a novel technical pathway for log parsing and anomaly detection, showcasing the substantial theoretical value and practical potential.

Keywords: log parsing, anomaly detection, RAG, prompt engineering, LLMs

Procedia PDF Downloads 36