Search results for: figure retrieval
716 Plagiarism Detection for Flowchart and Figures in Texts
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 461715 Performance Evaluation of Content Based Image Retrieval Using Indexed Views
Authors: Tahir Iqbal, Mumtaz Ali, Syed Wajahat Kareem, Muhammad Harris
Abstract:
Digital information is expanding in exponential order in our life. Information that is residing online and offline are stored in huge repositories relating to every aspect of our lives. Getting the required information is a task of retrieval systems. Content based image retrieval (CBIR) is a retrieval system that retrieves the required information from repositories on the basis of the contents of the image. Time is a critical factor in retrieval system and using indexed views with CBIR system improves the time efficiency of retrieved results.Keywords: content based image retrieval (CBIR), indexed view, color, image retrieval, cross correlation
Procedia PDF Downloads 463714 Retrieval-Induced Forgetting Effects in Retrospective and Prospective Memory in Normal Aging: An Experimental Study
Authors: Merve Akca
Abstract:
Retrieval-induced forgetting (RIF) refers to the phenomenon that selective retrieval of some information impairs memory for related, but not previously retrieved information. Despite age differences in retrieval-induced forgetting regarding retrospective memory being documented, this research aimed to highlight age differences in RIF of the prospective memory tasks for the first time. By using retrieval-practice paradigm, this study comparatively examined RIF effects in retrospective memory and event-based prospective memory in young and old adults. In this experimental study, a mixed factorial design with age group (Young, Old) as a between-subject variable, and memory type (Prospective, Retrospective) and item type (Practiced, Non-practiced) as within-subject variables was employed. Retrieval-induced forgetting was observed in the retrospective but not in the prospective memory task. Therefore, the results indicated that selective retrieval of past events led to suppression of other related past events in both age groups but not the suppression of memory for future intentions.Keywords: prospective memory, retrieval-induced forgetting, retrieval inhibition, retrospective memory
Procedia PDF Downloads 308713 Information Retrieval for Kafficho Language
Authors: Mareye Zeleke Mekonen
Abstract:
The Kafficho language has distinct issues in information retrieval because of its restricted resources and dearth of standardized methods. In this endeavor, with the cooperation and support of linguists and native speakers, we investigate the creation of information retrieval systems specifically designed for the Kafficho language. The Kafficho information retrieval system allows Kafficho speakers to access information easily in an efficient and effective way. Our objective is to conduct an information retrieval experiment using 220 Kafficho text files, including fifteen sample questions. Tokenization, normalization, stop word removal, stemming, and other data pre-processing chores, together with additional tasks like term weighting, were prerequisites for the vector space model to represent each page and a particular query. The three well-known measurement metrics we used for our word were Precision, Recall, and and F-measure, with values of 87%, 28%, and 35%, respectively. This demonstrates how well the Kaffiho information retrieval system performed well while utilizing the vector space paradigm.Keywords: Kafficho, information retrieval, stemming, vector space
Procedia PDF Downloads 49712 A Comparative Study of Approaches in User-Centred Health Information Retrieval
Authors: Harsh Thakkar, Ganesh Iyer
Abstract:
In this paper, we survey various user-centered or context-based biomedical health information retrieval systems. We present and discuss the performance of systems submitted in CLEF eHealth 2014 Task 3 for this purpose. We classify and focus on comparing the two most prevalent retrieval models in biomedical information retrieval namely: Language Model (LM) and Vector Space Model (VSM). We also report on the effectiveness of using external medical resources and ontologies like MeSH, Metamap, UMLS, etc. We observed that the LM based retrieval systems outperform VSM based systems on various fronts. From the results we conclude that the state-of-art system scores for MAP was 0.4146, P@10 was 0.7560 and NDCG@10 was 0.7445, respectively. All of these score were reported by systems built on language modeling approaches.Keywords: clinical document retrieval, concept-based information retrieval, query expansion, language models, vector space models
Procedia PDF Downloads 314711 Comparison of Crossover Types to Obtain Optimal Queries Using Adaptive Genetic Algorithm
Authors: Wafa’ Alma'Aitah, Khaled Almakadmeh
Abstract:
this study presents an information retrieval system of using genetic algorithm to increase information retrieval efficiency. Using vector space model, information retrieval is based on the similarity measurement between query and documents. Documents with high similarity to query are judge more relevant to the query and should be retrieved first. Using genetic algorithms, each query is represented by a chromosome; these chromosomes are fed into genetic operator process: selection, crossover, and mutation until an optimized query chromosome is obtained for document retrieval. Results show that information retrieval with adaptive crossover probability and single point type crossover and roulette wheel as selection type give the highest recall. The proposed approach is verified using (242) proceedings abstracts collected from the Saudi Arabian national conference.Keywords: genetic algorithm, information retrieval, optimal queries, crossover
Procedia PDF Downloads 284710 Content Based Face Sketch Images Retrieval in WHT, DCT, and DWT Transform Domain
Authors: W. S. Besbas, M. A. Artemi, R. M. Salman
Abstract:
Content based face sketch retrieval can be used to find images of criminals from their sketches for 'Crime Prevention'. This paper investigates the problem of CBIR of face sketch images in transform domain. Face sketch images that are similar to the query image are retrieved from the face sketch database. Features of the face sketch image are extracted in the spectrum domain of a selected transforms. These transforms are Discrete Cosine Transform (DCT), Discrete Wavelet Transform (DWT), and Walsh Hadamard Transform (WHT). For the performance analyses of features selection methods three face images databases are used. These are 'Sheffield face database', 'Olivetti Research Laboratory (ORL) face database', and 'Indian face database'. The City block distance measure is used to evaluate the performance of the retrieval process. The investigation concludes that, the retrieval rate is database dependent. But in general, the DCT is the best. On the other hand, the WHT is the best with respect to the speed of retrieving images.Keywords: Content Based Image Retrieval (CBIR), face sketch image retrieval, features selection for CBIR, image retrieval in transform domain
Procedia PDF Downloads 484709 Secure Image Retrieval Based on Orthogonal Decomposition under Cloud Environment
Authors: Y. Xu, L. Xiong, Z. Xu
Abstract:
In order to protect data privacy, image with sensitive or private information needs to be encrypted before being outsourced to the cloud. However, this causes difficulties in image retrieval and data management. A secure image retrieval method based on orthogonal decomposition is proposed in the paper. The image is divided into two different components, for which encryption and feature extraction are executed separately. As a result, cloud server can extract features from an encrypted image directly and compare them with the features of the queried images, so that the user can thus obtain the image. Different from other methods, the proposed method has no special requirements to encryption algorithms. Experimental results prove that the proposed method can achieve better security and better retrieval precision.Keywords: secure image retrieval, secure search, orthogonal decomposition, secure cloud computing
Procedia PDF Downloads 476708 Graph Codes - 2D Projections of Multimedia Feature Graphs for Fast and Effective Retrieval
Authors: Stefan Wagenpfeil, Felix Engel, Paul McKevitt, Matthias Hemmje
Abstract:
Multimedia Indexing and Retrieval is generally designed and implemented by employing feature graphs. These graphs typically contain a significant number of nodes and edges to reflect the level of detail in feature detection. A higher level of detail increases the effectiveness of the results but also leads to more complex graph structures. However, graph-traversal-based algorithms for similarity are quite inefficient and computation intensive, especially for large data structures. To deliver fast and effective retrieval, an efficient similarity algorithm, particularly for large graphs, is mandatory. Hence, in this paper, we define a graph-projection into a 2D space (Graph Code) as well as the corresponding algorithms for indexing and retrieval. We show that calculations in this space can be performed more efficiently than graph-traversals due to a simpler processing model and a high level of parallelization. In consequence, we prove that the effectiveness of retrieval also increases substantially, as Graph Codes facilitate more levels of detail in feature fusion. Thus, Graph Codes provide a significant increase in efficiency and effectiveness (especially for Multimedia indexing and retrieval) and can be applied to images, videos, audio, and text information.Keywords: indexing, retrieval, multimedia, graph algorithm, graph code
Procedia PDF Downloads 150707 Leveraging Quality Metrics in Voting Model Based Thread Retrieval
Authors: Atefeh Heydari, Mohammadali Tavakoli, Zuriati Ismail, Naomie Salim
Abstract:
Seeking and sharing knowledge on online forums have made them popular in recent years. Although online forums are valuable sources of information, due to variety of sources of messages, retrieving reliable threads with high quality content is an issue. Majority of the existing information retrieval systems ignore the quality of retrieved documents, particularly, in the field of thread retrieval. In this research, we present an approach that employs various quality features in order to investigate the quality of retrieved threads. Different aspects of content quality, including completeness, comprehensiveness, and politeness, are assessed using these features, which lead to finding not only textual, but also conceptual relevant threads for a user query within a forum. To analyse the influence of the features, we used an adopted version of voting model thread search as a retrieval system. We equipped it with each feature solely and also various combinations of features in turn during multiple runs. The results show that incorporating the quality features enhances the effectiveness of the utilised retrieval system significantly.Keywords: content quality, forum search, thread retrieval, voting techniques
Procedia PDF Downloads 207706 Unsupervised Domain Adaptive Text Retrieval with Query Generation
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. Experiments show that our approach is more robust than previous methods in target domains that require less unlabeled data.Keywords: dense retrieval, query generation, unsupervised training, text retrieval
Procedia PDF Downloads 63705 Role of Natural Language Processing in Information Retrieval; Challenges and Opportunities
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 332704 Merging of Results in Distributed Information Retrieval Systems
Authors: Larbi Guezouli, Imane Azzouz
Abstract:
This work is located in the domain of distributed information retrieval ‘DIR’. A simplified view of the DIR requires a multi-search in a set of collections, which forces the system to analyze results found in these collections, and merge results back before sending them to the user in a single list. Our work is to find a fusion method based on the relevance score of each result received from collections and the relevance of the local search engine of each collection.Keywords: information retrieval, distributed IR systems, merging results, datamining
Procedia PDF Downloads 329703 Content Based Video Retrieval System Using Principal Object Analysis
Authors: Van Thinh Bui, Anh Tuan Tran, Quoc Viet Ngo, The Bao Pham
Abstract:
Video retrieval is a searching problem on videos or clips based on content in which they are relatively close to an input image or video. The application of this retrieval consists of selecting video in a folder or recognizing a human in security camera. However, some recent approaches have been in challenging problem due to the diversity of video types, frame transitions and camera positions. Besides, that an appropriate measures is selected for the problem is a question. In order to overcome all obstacles, we propose a content-based video retrieval system in some main steps resulting in a good performance. From a main video, we process extracting keyframes and principal objects using Segmentation of Aggregating Superpixels (SAS) algorithm. After that, Speeded Up Robust Features (SURF) are selected from those principal objects. Then, the model “Bag-of-words” in accompanied by SVM classification are applied to obtain the retrieval result. Our system is performed on over 300 videos in diversity from music, history, movie, sports, and natural scene to TV program show. The performance is evaluated in promising comparison to the other approaches.Keywords: video retrieval, principal objects, keyframe, segmentation of aggregating superpixels, speeded up robust features, bag-of-words, SVM
Procedia PDF Downloads 292702 Local Texture and Global Color Descriptors for Content Based Image Retrieval
Authors: Tajinder Kaur, Anu Bala
Abstract:
An image retrieval system is a computer system for browsing, searching, and retrieving images from a large database of digital images a new algorithm meant for content-based image retrieval (CBIR) is presented in this paper. The proposed method combines the color and texture features which are extracted the global and local information of the image. The local texture feature is extracted by using local binary patterns (LBP), which are evaluated by taking into consideration of local difference between the center pixel and its neighbors. For the global color feature, the color histogram (CH) is used which is calculated by RGB (red, green, and blue) spaces separately. In this paper, the combination of color and texture features are proposed for content-based image retrieval. The performance of the proposed method is tested on Corel 1000 database which is the natural database. The results after being investigated show a significant improvement in terms of their evaluation measures as compared to LBP and CH.Keywords: color, texture, feature extraction, local binary patterns, image retrieval
Procedia PDF Downloads 358701 A Graph-Based Retrieval Model for Passage Search
Authors: Junjie Zhong, Kai Hong, Lei Wang
Abstract:
Passage Retrieval (PR) plays an important role in many Natural Language Processing (NLP) tasks. Traditional efficient retrieval models relying on exact term-matching, such as TF-IDF or BM25, have nowadays been exceeded by pre-trained language models which match by semantics. Though they gain effectiveness, deep language models often require large memory as well as time cost. To tackle the trade-off between efficiency and effectiveness in PR, this paper proposes Graph Passage Retriever (GraphPR), a graph-based model inspired by the development of graph learning techniques. Different from existing works, GraphPR is end-to-end and integrates both term-matching information and semantics. GraphPR constructs a passage-level graph from BM25 retrieval results and trains a GCN-like model on the graph with graph-based objectives. Passages were regarded as nodes in the constructed graph and were embedded in dense vectors. PR can then be implemented using embeddings and a fast vector-similarity search. Experiments on a variety of real-world retrieval datasets show that the proposed model outperforms related models in several evaluation metrics (e.g., mean reciprocal rank, accuracy, F1-scores) while maintaining a relatively low query latency and memory usage.Keywords: efficiency, effectiveness, graph learning, language model, passage retrieval, term-matching model
Procedia PDF Downloads 130700 Biomedical Definition Extraction Using Machine Learning with Synonymous Feature
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 484699 Domain Adaptive Dense Retrieval with Query Generation
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 92698 Similarity Based Retrieval in Case Based Reasoning for Analysis of Medical Images
Authors: M. Dasgupta, S. Banerjee
Abstract:
Content Based Image Retrieval (CBIR) coupled with Case Based Reasoning (CBR) is a paradigm that is becoming increasingly popular in the diagnosis and therapy planning of medical ailments utilizing the digital content of medical images. This paper presents a survey of some of the promising approaches used in the detection of abnormalities in retina images as well in mammographic screening and detection of regions of interest in MRI scans of the brain. We also describe our proposed algorithm to detect hard exudates in fundus images of the retina of Diabetic Retinopathy patients.Keywords: case based reasoning, exudates, retina image, similarity based retrieval
Procedia PDF Downloads 339697 A Framework of Product Information Service System Using Mobile Image Retrieval and Text Mining Techniques
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 352696 Selection of Relevant Servers in Distributed Information Retrieval System
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 301695 Thermoelectric Properties of Spark Plasma Sintered Te Doped Cu₃SbSe₄: Promising Thermoelectric Material
Authors: Kriti Tyagi, Bhasker Gahtori
Abstract:
Various groups have attempted on enhancing the thermoelectric figure-of-merit (ZT) of the Cu₃SbSe₄ compound by employing doping process. Efforts are made to study the thermoelectric performance of Cu₃SbSe₄ material doped with Te in different compositions (i. e. Cu₃Sb₁₋ₓTeₓSe₄, x = 0.005, 0.01, 0.015, 0.02). The different doping concentration has been selected to identify the suitable doping to increase the thermoelectric performance. Compared to pristine Cu₃SbSe₄, an enhancement of thermoelectric figure-of-merit was achieved for 0.005 Te doped Cu₃SbSe₄. This improvement can be attributed to the reduction of thermal conductivity for 0.005 Te doped Cu₃SbSe₄.Keywords: figure-of-merit, polycrystalline, thermal conductivity, thermoelectric
Procedia PDF Downloads 234694 Algorithm for Information Retrieval Optimization
Authors: Kehinde K. Agbele, Kehinde Daniel Aruleba, Eniafe F. Ayetiran
Abstract:
When using Information Retrieval Systems (IRS), users often present search queries made of ad-hoc keywords. It is then up to the IRS to obtain a precise representation of the user’s information need and the context of the information. This paper investigates optimization of IRS to individual information needs in order of relevance. The study addressed development of algorithms that optimize the ranking of documents retrieved from IRS. This study discusses and describes a Document Ranking Optimization (DROPT) algorithm for information retrieval (IR) in an Internet-based or designated databases environment. Conversely, as the volume of information available online and in designated databases is growing continuously, ranking algorithms can play a major role in the context of search results. In this paper, a DROPT technique for documents retrieved from a corpus is developed with respect to document index keywords and the query vectors. This is based on calculating the weight (Keywords: information retrieval, document relevance, performance measures, personalization
Procedia PDF Downloads 237693 Content-Based Image Retrieval Using HSV Color Space Features
Authors: Hamed Qazanfari, Hamid Hassanpour, Kazem Qazanfari
Abstract:
In this paper, a method is provided for content-based image retrieval. Content-based image retrieval system searches query an image based on its visual content in an image database to retrieve similar images. In this paper, with the aim of simulating the human visual system sensitivity to image's edges and color features, the concept of color difference histogram (CDH) is used. CDH includes the perceptually color difference between two neighboring pixels with regard to colors and edge orientations. Since the HSV color space is close to the human visual system, the CDH is calculated in this color space. In addition, to improve the color features, the color histogram in HSV color space is also used as a feature. Among the extracted features, efficient features are selected using entropy and correlation criteria. The final features extract the content of images most efficiently. The proposed method has been evaluated on three standard databases Corel 5k, Corel 10k and UKBench. Experimental results show that the accuracy of the proposed image retrieval method is significantly improved compared to the recently developed methods.Keywords: content-based image retrieval, color difference histogram, efficient features selection, entropy, correlation
Procedia PDF Downloads 240692 Urdu Text Extraction Method from Images
Authors: Samabia Tehsin, Sumaira Kausar
Abstract:
Due to the vast increase in the multimedia data in recent years, efficient and robust retrieval techniques are needed to retrieve and index images/ videos. Text embedded in the images can serve as the strong retrieval tool for images. This is the reason that text extraction is an area of research with increasing attention. English text extraction is the focus of many researchers but very less work has been done on other languages like Urdu. This paper is focusing on Urdu text extraction from video frames. This paper presents a text detection feature set, which has the ability to deal up with most of the problems connected with the text extraction process. To test the validity of the method, it is tested on Urdu news dataset, which gives promising results.Keywords: caption text, content-based image retrieval, document analysis, text extraction
Procedia PDF Downloads 506691 SIFT and Perceptual Zoning Applied to CBIR Systems
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 305690 Image Retrieval Based on Multi-Feature Fusion for Heterogeneous Image Databases
Authors: N. W. U. D. Chathurani, Shlomo Geva, Vinod Chandran, Proboda Rajapaksha
Abstract:
Selecting an appropriate image representation is the most important factor in implementing an effective Content-Based Image Retrieval (CBIR) system. This paper presents a multi-feature fusion approach for efficient CBIR, based on the distance distribution of features and relative feature weights at the time of query processing. It is a simple yet effective approach, which is free from the effect of features' dimensions, ranges, internal feature normalization and the distance measure. This approach can easily be adopted in any feature combination to improve retrieval quality. The proposed approach is empirically evaluated using two benchmark datasets for image classification (a subset of the Corel dataset and Oliva and Torralba) and compared with existing approaches. The performance of the proposed approach is confirmed with the significantly improved performance in comparison with the independently evaluated baseline of the previously proposed feature fusion approaches.Keywords: feature fusion, image retrieval, membership function, normalization
Procedia PDF Downloads 342689 Little Retrieval Augmented Generation for Named Entity Recognition: Toward Lightweight, Generative, Named Entity Recognition Through Prompt Engineering, and Multi-Level Retrieval Augmented Generation
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 Mistral-v0.3, Llama-3, and Phi-3, for Generative Named Entity Recognition (GNER). Our proposed Multi-Level Information Retrieval method achieves notable improvements over finetuned entity-level and sentence-level methods. We consider recent developments at the cross roads of prompt engineering and Retrieval Augmented Generation (RAG), such as EmotionPrompt. 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 14688 Enhanced Arabic Semantic Information Retrieval System Based on Arabic Text Classification
Authors: A. Elsehemy, M. Abdeen , T. Nazmy
Abstract:
Since the appearance of the Semantic web, many semantic search techniques and models were proposed to exploit the information in ontology to enhance the traditional keyword-based search. Many advances were made in languages such as English, German, French and Spanish. However, other languages such as Arabic are not fully supported yet. In this paper we present a framework for ontology based information retrieval for Arabic language. Our system consists of four main modules, namely query parser, indexer, search and a ranking module. Our approach includes building a semantic index by linking ontology concepts to documents, including an annotation weight for each link, to be used in ranking the results. We also augmented the framework with an automatic document categorizer, which enhances the overall document ranking. We have built three Arabic domain ontologies: Sports, Economic and Politics as example for the Arabic language. We built a knowledge base that consists of 79 classes and more than 1456 instances. The system is evaluated using the precision and recall metrics. We have done many retrieval operations on a sample of 40,316 documents with a size 320 MB of pure text. The results show that the semantic search enhanced with text classification gives better performance results than the system without classification.Keywords: Arabic text classification, ontology based retrieval, Arabic semantic web, information retrieval, Arabic ontology
Procedia PDF Downloads 519687 Preliminary Study on Analysis of Pinching Motion Actuated by Electro-Active Polymers
Authors: Doo W. Lee, Soo J. Lee, Bye R. Yoon, Jae Y. Jho, Kyehan Rhee
Abstract:
Hand exoskeletons have been developed in order to assist daily activities for disabled and elder people. A figure exoskeleton was developed using ionic polymer metal composite (IPMC) actuators, and the performance of it was evaluated in this study. In order to study dynamic performance of a finger dummy performing pinching motion, force generating characteristics of an IPMC actuator and pinching motion of a thumb and index finger dummy actuated by IMPC actuators were analyzed. The blocking force of 1.54 N was achieved under 4 V of DC. A thumb and index finger dummy, which has one degree of freedom at the proximal joint of each figure, was manufactured by a three dimensional rapid prototyping. Each figure was actuated by an IPMC actuator, and the maximum fingertip force was 1.18 N. Pinching motion of a dummy was analyzed by two video cameras in vertical top and horizontal left end view planes. A figure dummy powered by IPMC actuators could perform flexion and extension motion of an index figure and a thumb.Keywords: finger exoskeleton, ionic polymer metal composite, flexion and extension, motion analysis
Procedia PDF Downloads 232