Representing Texts as Contextualized Entity-Centric Linked Data Graphs

This paper proposes a semantic information extraction technology model system based on BERT, aiming to solve the problem of semantic understanding and information extraction in online public opinion analysis. The system design includes data collection, preprocessing, semantic information extraction and result display modules, using the BERT model to capture the deep semantic relationship of the text and enhance the ability to understand complex semantics and contextual information. The data collection module covers multiple sources such as social media, news comments and forum posts, and ensures the high quality and diversity of data through real-time crawling and cleaning. The semantic information extraction module is based on the multi-head attention mechanism of BERT, which can effectively capture the emotional tendency, topic information and potential intention in the public opinion text. The experiment verifies the system performance based on 1 million online public opinion data. The results show that in the semantic information extraction task, the accuracy of the BERT-based model is improved by 22.4%, the recall rate is improved by 19.8%, and the F1 value reaches 91.7<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">%</sup>, which is significantly better than traditional methods such as TF-IDF and Word2Vec. The sentiment classification module has an accuracy of 93.1%, achieving accurate recognition of positive, negative and neutral emotions. The processing time of a single piece of public opinion text is reduced by an average of 25.6%, indicating the high efficiency of the system in large-scale data processing. The simulation test verifies the system's stable operation capability in the scenario of 100,000 new public opinion data per day, with a delay of less than 1 second, which can meet the needs of real-time public opinion analysis.

Zero-shot composed image retrieval (ZS-CIR) is a rapidly growing area with significant practical applications, allowing users to retrieve a target image by providing a reference image and a relative caption describing the desired modifications. Existing ZS-CIR methods often struggle to capture fine-grained changes and integrate visual and semantic information effectively. They primarily rely on either transforming the multimodal query into a single text using image-to-text models or employing large language models for target image description generation, approaches that often fail to capture complementary visual information and complete semantic context. To address these limitations, we propose a novel Fine-Grained Zero-Shot Composed Image Retrieval method with Complementary VisualSemantic Integration (CVSI). Specifically, CVSI leverages three key components: (1) Visual Information Extraction, which not only extracts global image features but also uses a pre-trained mapping network to convert the image into a pseudo token, combining it with the modification text and the objects most likely to be added. (2) Semantic Information Extraction, which involves using a pre-trained captioning model to generate multiple captions for the reference image, followed by leveraging an LLM to generate the modified captions and the objects most likely to be added. (3) Complementary Information Retrieval, which integrates information extracted from both the query and database images to retrieve the target image, enabling the system to efficiently handle retrieval queries in a variety of situations. Extensive experiments on three public datasets (e.g., CIRR, CIRCO, and FashionIQ) demonstrate that CVSI significantly outperforms existing state-of-the-art methods. Our code is available at https://github.com/yyc6631/CVSI.

Ever increasing volumes of media content and the desire to extract information from media archives motivate the studies into semantic audio information mining. Much research in this filed concerns development of bespoke systems, in which soundtracks are exclusively classified and segmented, and a specific type of sound is recognized and analyzed. This approach however is detrimental to the complete extraction of all relevant semantic information and audio scene analysis. The current study addresses the issues of soundtracks with overlapped music, speech and ambient sounds, and explores how MARSYAS (Music Analysis, Retrieval and Synthesis for Audio Signals) can be extended to mixed and overlapped soundtrack applications. The MARSYAS has been adapted to this application by means of adopting additional speech cleaning algorithms. The proposed new system can analyze arbitrary soundtracks and timestamp the occurrence of music and speech, allowing overlaps, in the form of a “sound score” for further recognition methods to extract music score and text information. Validation tests have shown that the new system handles overlapping cases and is therefore capable of extracting more information than other existing methods.

As a result of the rapid development of smartphone-based indoor localization technology, location-based services in indoor spaces have become a topic of interest. However, to date, the rich data resulting from indoor localization and navigation applications have not been fully exploited, which is significant for trajectory correction and advanced indoor map information extraction. In this paper, an integrated location acquisition method utilizing activity recognition and semantic information extraction is proposed for indoor mobile localization. The location acquisition method combines pedestrian dead reckoning (PDR), human activity recognition (HAR) and landmarks to acquire accurate indoor localization information. Considering the problem of initial position determination, a hidden Markov model (HMM) is utilized to infer the user’s initial position. To provide an improved service for further applications, the landmarks are further assigned semantic descriptions by detecting the user’s activities. The experiments conducted in this study confirm that a high degree of accuracy for a user’s indoor location can be obtained. Furthermore, the semantic information of a user’s trajectories can be extracted, which is extremely useful for further research into indoor location applications.

Addressed in this paper is the issue of semantic relationship extraction from semi-structured documents. Many research efforts have been made so far on the semantic information extraction. However, much of the previous work focuses on detecting `isolated' semantic information by making use of linguistic analysis or linkage information in web pages and limited research has been done on extracting semantic relationship from the semi-structured documents. In this paper, we propose a method for semantic relationship extraction by using the logical information in the semi-structured document (semi-structured document usually has various types of structure information, e.g. a semi-structured document may be hierarchical laid out). To the best of our knowledge, extracting semantic relationships by using logical information has not been investigated previously. A probabilistic approach has been proposed in the paper. Features used in the probabilistic model have been defined.

Recognizing and extracting meaningful information from Web unstructured documents, taking into account their semantics, is an important problem of information and knowledge management. This paper describes H\(\imath\)LeX, a system implementing a novel logic-based approach to information extraction from unstructured documents. The approach adopted in the H\(\imath\)LeX system is founded on a new two-dimensional representation of documents, and heavily exploits DLP + - an extension of disjunctive logic programming for ontology representation and reasoning, which has been recently implemented on top of the DLV reasoning environment. Unlike previous systems, which are mainly syntactic, H\(\imath\)LeX combines both semantic and syntactic knowledge for a powerful information extraction. Ontologies, representing the semantics of information to be extracted, are encoded in DLP + , while the extraction patterns are expressed using regular expressions and an ad hoc two-dimensional grammar. The execution of DLP + reasoning modules, encoding the grammar expressions, yields the actual extraction of information from the input document. H\(\imath\)LeX allows the semantic information extraction from both HTML pages and flat text documents by using synthetic and very expressive extraction patterns.

© 2016 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

Ontologies play an important role of the applications in recent years, especially on the Semantic Web, Information Retrieval, Information Extraction, and Question Answering. Ontologies are used in order to specify the knowledge that is exchanged and shared between the different systems. Ontologies define the formal semantics of the terms used for describing data, and the relations between these terms. Hence, one of the important steps for building the domain specific ontology is to construct the semantic relations among the terms of the ontology. This paper represents our proposed method for automatic semantic relation extraction from text documents of the ACM Digital Library. A random sample among 170 categories of ACM categories is used to evaluate our proposed method. Results generated show that our proposed method achieves high precision.

The work presents new possibilities for making semantic description and interpretation of some medical visualization with the use of Computational Intelligence linguistic formalisms. The methodology described in this work makes possible to find, for each considered biological 3D structure, its semantic description whose elements make reference to the medical significance of the entire structure described, while at the same time refrain from the formal differences (i.e. appearance and shape) of individual visualisations. Such methodology may be further used for attaining other goals related to computer-assisted semantic interpretation of selected elements and/or the entire 3D structure of the coronary vascular tree. The obtained semantic information allows to make a description of the structure, focused on the semantics of various heart muscle lesions. Thanks to these, the analysis conducted allows fast and automated interpretation of the semantics of various morphological changes in the coronary vascular tree. Especially it is possible to detect stenoses in the lumen of the vessels that can cause critical decrease of blood supply to extensive or especially important fragments of the heart muscle. The basis for the construction of 3D reconstructions of biological objects used in this work are visualisations obtained from helical CT scans, yet the method itself may be applied also for other methods of medical 3D images acquisition.

Information extraction (IE) is a technique for extracting structured data or knowledge from unstructured data by determining the references to words as well as the relationships between them. IE systems can be used to directly extract knowledge from a text corpus, or to extract useful data from a pile of documents which moreover, can be further analyzed with deep learning algorithms to discover more patterns. In today's era, the internet exhibits several characteristics including unstructured data and noisy text information. Unstructured data may contain audio, image, text, video, etc. Information extraction can be useful for topic detection (Twitter, Digital libraries), Breast Cancer detection and many more applications. The proposed system can exploit deep learning for information extraction using image as well as text and can significantly improve its performance with the inclusion of structured and unstructured data. This paper focuses on extraction of information from unstructured data using various deep learning models and concepts of Natural Language Processing (NLP), Long Short Term Networks (LSTM) and for topic extraction used Latent Dirichlet Allocation (LDA) etc.

Adverse Outcome Pathways (AOPs) provide a structured framework for linking mechanistic events across biological organization levels, supporting chemical hazard identification and regulatory decision-making in Next-Generation Risk Assessment (NGRA). However, AOP development remains labor-intensive, requiring extensive literature searching and expert review to identify relevant events and supporting evidence. Existing text mining tools often operate on limited datasets, lack interactive capabilities, and miss contextually relevant studies. To address these challenges, we present S2CIE (Semantic & Syntactic Context-based Information Extraction), an interactive, real-time platform for extracting mechanistic information from biomedical literature. S2CIE annotates PubMed abstracts (32 million) at the word level with grammatical, entity-type, and dependency annotations, enabling custom extraction rules based on syntactic patterns, and employ semantic retrieval based on user specific query. The system supports near real-time querying and integrates entity recognition and visual exploration tools. We demonstrate S2CIE's utility through four case studies. First, we identified 110 chemicals linked to liver steatosis/cholestasis with 98.79% precision, extracting chemical and PPAR (peroxisome proliferator-activated receptors) interactions as molecular initiating events. Second enrichment analysis of literature derived genes and successful mapping with AOPs. Third, comparative analysis against AOP-HelpFinder for key event relationships in AOP 220 showed 42.2% increased evidence capture (1,614 vs 1,135 abstracts) with 99% reduced retrieval time. Fourth, large-scale extraction of post-translational modification events demonstrated domain-agnostic applicability beyond toxicology. S2CIE accelerates AOP evidence gathering, while maintaining transparency and auditability essential for regulatory application. S2CIE is available as open source through an API and as web application at https://dev.s2cie.insilicohub.org/.

SLAM is a critical technology for enabling autonomous navigation and positioning in unmanned vehicles. Traditional visual simultaneous localization and mapping algorithms are built upon the assumption of a static scene, overlooking the impact of dynamic targets within real-world environments. Interference from dynamic targets can significantly degrade the system's localization accuracy or even lead to tracking failure. To address these issues, we propose a dynamic visual SLAM system named BY-SLAM, which is based on BEBLID and semantic information extraction. Initially, the BEBLID descriptor is introduced to describe Oriented FAST feature points, enhancing both feature point matching accuracy and speed. Subsequently, FasterNet replaces the backbone network of YOLOv8s to expedite semantic information extraction. By using the results of DBSCAN clustering object detection, a more refined semantic mask is obtained. Finally, by leveraging the semantic mask and epipolar constraints, dynamic feature points are discerned and eliminated, allowing for the utilization of only static feature points for pose estimation and the construction of a dense 3D map that excludes dynamic targets. Experimental evaluations are conducted on both the TUM RGB-D dataset and real-world scenarios and demonstrate the effectiveness of the proposed algorithm at filtering out dynamic targets within the scenes. On average, the localization accuracy for the TUM RGB-D dataset improves by 95.53% compared to ORB-SLAM3. Comparative analyses against classical dynamic SLAM systems further corroborate the improvement in localization accuracy, map readability, and robustness achieved by BY-SLAM.

As a key representation model of knowledge, ontology has been widely used in a lot of NLP related tasks, such as semantic parsing, information extraction and text mining etc. In this paper, we study the task of ontology matching, which concentrates on finding semantically related entities between different ontologies that describe the same domain, to solve the semantic heterogeneity problem. Previous works exploit different kinds of descriptions of an entity in ontology directly and separately to find the correspondences without considering the higher level correlations between the descriptions. Besides, the structural information of ontology haven’t been utilized adequately for ontology matching. We propose in this paper an ontology matching approach, named ERSOM, which mainly includes an unsupervised representation learning method based on the deep neural networks to learn the general representation of the entities and an iterative similarity propagation method that takes advantage of more abundant structure information of the ontology to discover more mappings. The experimental results on the datasets from Ontology Alignment Evaluation Initiative (OAEI1) show that ERSOM achieves a competitive performance compared to the state-of-the-art ontology matching systems. The OAEI is an international initiative organizing annual campaigns for evaluating ontology matching systems. All of the ontologies provided by OAEI are described in OWL-DL language, and like most of the other participates our ERSOM also manages the OWL ontology in its current version. OAEI: http://oaei.ontologymatching.org/

The Web represents a valuable data source of information that is presented mainly as unstructured text. The extraction of structured and valuable information from sources such as the Web is an important challenge for the Semantic Web and Information Extraction areas, where elements representing real-world objects (aka named entities) and their relations need to be extracted from text and formally represented through RDF triples. Thus, extracting such information from the Web is manually unfeasible due to its large scale and heterogeneity of domains. In this sense, Open Information Extraction (OIE) is an independent domain task based on patterns to extract any kind of relation between named entities. Hence, one step further is to transform such relations into RDF triples. This paper proposes a method to represent relations obtained by an OIE approach into RDF triples. The method is based on the extraction of named entities, their relation, and contextual information from an input sentence and a set of defined rules that lead to map the extracted elements with resources from a Knowledge Base of the Semantic Web. The evaluation demonstrates promising results regarding the extraction and representation of information.

A survey of the key approaches to the semantic processing of mathematical texts is presented. A software platform prototype for the electronic storage of mathematical documents, which is based on the linked open-data (LOD) model and uses semantic information for data management, including formula-fragment searching, is proposed. The analysis of mathematical documents and the extraction of semantic information from the latter are carried out based on the electronic collection of the Izv. Vyssh. Uchebn. Zaved., Mat. (1995---2009) using special-purpose ontologies, metadata representation in the RDF (Resource Description Framework) format, and integration with existing LOD sets.