Representing information need with semantic relations

An electrophysiological (ERP) component, the recognition potential, in the assessment of brain semantic networks in patients with schizophrenia

TechWordNet: Development of semantic relation for technology information analysis using F-term and natural language processing

In the past decade, the prosperity of the World Wide Web has led to fast explosion of information, and there is a long-standing demand on how to access such a huge volume of information effectively and efficiently. Information Retrieval (IR) aims to tackle the challenge by exploring approaches to obtain relevant information items (e.g., documents) relevant to a given information need (e.g., query) from a huge collection of textual data (e.g., the Web). Named entity (e.g., person, location, product, event, organization) is a type of term compound widely existing in textual data. Recent advances in Information Extraction make it possible to extract entities from large volume of free text efficiently, and the research community are actively exploring whether entities would contribute to the retrieval effectiveness. In this thesis, we investigate how to leverage entities to improve retrieval in several directions. We start with finding entities with certain semantic relation, which aims at retrieving entities and their associated attributes to meet user's information need directly. This is different from traditional search paradigm in which only documents are retrieved. Entity retrieval is performed by first retrieving a list of documents and then extracting entities from those documents. We propose a novel probabilistic framework which leverages supporting documents as bridge to model the relevance between query and entities and rank entities accordingly. On the other side, we also explore how to leverage entities to improve effectiveness of ad hoc document retrieval in two directions. The first direction is entity-centric query expansion. We find related entities of query, and perform query expansion using the names and relations of related entities. Significant improvements over several state-of-the-art feedback models could be observed on multiple data collections. Besides, we explore another direction: entity-centric relevance modeling. We propose a novel retrieval approach, i.e., Latent Entity Space (LES), which models the relevance by leveraging entity profiles to represent semantic content of documents and queries. Experimental results over several TREC collections show that LES is effective on capturing latent semantic content and can significantly improve the search accuracy of several state-of-the-art retrieval models for entity-bearing queries. This thesis presents a series of research efforts on entity centric information retrieval in several directions, and reveals promising potential of entities on improving the retrieval effectiveness. With the fast curation of high-quality knowledge base, more information about entities could be easily accessed and integrated into retrieval models. We hope our work could serve as guideline for future work on leveraging entities to improve information retrieval in more applications.


 
 
 This paper devoted the problem of identifying a semantic similarity degree or difference of text in cybersecurity field. The paper presents a method for comparing text documents based on the formation and comparison of the corresponding semantic networks. The directed weighted network of terms, where the nodes of such networks are key terms of the text, and edges are semantic relationships between these terms in the text are considered as a semantic network. The algorithm for formation semantic networks as one of the types of ontologies is also presented. Formation of network of term includes pre-processing of text data, extraction of key terms, construction of undirected network of terms (using the algorithm of horizontal visibility graph), determining undirected connections between terms, and further determining the directions of connections and their weight values. The Frobenius norm of the difference of matrices corresponding to the semantic networks is considered to compare the semantic networks. An identifying the critically different texts that can have similar keywords but different semantic between them is important to ensure cybersecurity. Also, the proposed approach can be helpful while solving the problem of accumulating text data semantically similar in content. In general, this approach can also be used in systems of automatic information retrieval to determine the degree of similarity or difference in the structure and semantics of texts and identify the sources of information that have a destructive impact on the information space.
 
 

The Information Retrieval (IR) problem can be described as the quest to find the set of relevant information objects corresponding to a given information need, which is represented by a request. IR begins with a user who wishes to satisfy an information need. The information need is typically formulated in the form of a request, denoted by q. The intention is that the request q be as good as possible description of the information need N. The information being queried is modelled as a set of information carriers, or documents. An often used premise in IR is the following: if a given document d is about the request q, then there is a high likelihood that d is relevant with respect to the associated information need. Thus, the IR problem is reduced to deciding the aboutness relation between documents and requests. Many IR models have been developed, and there is a wide variation in how they determine aboutness. A common approach is to equate aboutness with overlap, meaning if there is sufficient overlap between the document and the query, the document is deemed to be about the query. The degree of overlap determined by the retrieval model is usually expressed as a real number between zero (no overlap) and unity (complete overlap). In most models, “sufficient” overlap is not prescribed by the model but by experimentation within a given IR setting. Such experimentation may lead to the conclusion, say, that sufficient overlap is apparent when the overlap measure is greater than α, 0 < α ≤ 1. The value α varies from setting to setting.

The main goal of information retrieval (IR) is to satisfy information need (IN). IN refers to a complex concept: at the very initial state of the phenomenon (that is, at a visceral level), even the searcher may not be aware of its existence. Thus, despite advances in the past few decades in both the IR and relevant scientific communities, we do not fully understand how an IN emerges and how it is physically manifested. In this article we aim to inform a holistic view of the realization of IN using functional magnetic resonance imaging. We collected new data of brain activity of 24 participants while they formulated and stated a realization of IN in a Question Answering task, focusing on a distributed set of brain regions associated with activities related to IN, found in our previous study. Results of a functional connectivity analysis led us to propose a neuropsychological model of the realization of IN. Our model consists of three components: (a) a successful memory retrieval component, (b) an information flow regulation component, and (c) a high‐level perception component. We believe this study constitutes an important step in unraveling the nature of IN and how to better satisfy IN.

Ontology is the basis of sharing and reusing knowledge on the Semantic Web, and ontology-based semantic retrieval is a hotspot of current research. Fuzzy ontology is an extension of domain ontology for solving the uncertainty problems. To represent fuzzy knowledge more effectively, this paper presents a new series of fuzzy ontology models that consists of fuzzy domain ontology and fuzzy linguistic variable ontologies, considering semantic relationships of concepts, including set relation, order relation, equivalence relation and semantic association relation etc. The process to construct linguistic variables ontology is discussed. Using ontology and RDFS, the knowledge model for product information is created. To achieve semantic retrieval, the semantic query expansion in SeRQL is constructed by semantic relations between fuzzy concepts. The application shows that these models can overcome the localization of other fuzzy ontology models, and this research facilitates the fuzzy knowledge sharing and semantic retrieval on the Semantic Web.

For bridging the gap between information retrieval (IR) and databases (DB), this article focuses on the logical view. We claim that IR should adopt three major concepts from DB, namely inference, vague predicates and expressive query languages. By regarding IR as uncertain inference, probabilistic versions of relational algebra and Datalog yield very powerful inference mechanisms for IR as well as allowing for more flexible systems. For dealing with various media and data types, vague predicates form a natural extension of text retrieval methods to attribute values, thus switching from propositional to predicate logic. A more expressive IR query language should support joins, be able to compute aggregated results, and allow for restructuring of the result objects.

Measuring the similarity between implicit semantic relations is an important task in information retrieval and natural language processing. For example, consider the situation where you know an entity-pair (e.g. Google, YouTube), between which a particular relation holds (e.g. acquisition), and you are interested in retrieving other entity-pairs for which the same relation holds (e.g. Yahoo, Inktomi). Existing keyword-based search engines cannot be directly applied in this case because in keyword-based search, the goal is to retrieve documents that are relevant to the words used in the query -- not necessarily to the relations implied by a pair of words. Accurate measurement of relational similarity is an important step in numerous natural language processing tasks such as identification of word analogies, and classification of noun-modifier pairs. We propose a method that uses Web search engines to efficiently compute the relational similarity between two pairs of words. Our method consists of three components: representing the various semantic relations that exist between a pair of words using automatically extracted lexical patterns, clustering the extracted lexical patterns to identify the different semantic relations implied by them, and measuring the similarity between different semantic relations using an inter-cluster correlation matrix. We propose a pattern extraction algorithm to extract a large number of lexical patterns that express numerous semantic relations. We then present an efficient clustering algorithm to cluster the extracted lexical patterns. Finally, we measure the relational similarity between word-pairs using inter-cluster correlation. We evaluate the proposed method in a relation classification task. Experimental results on a dataset covering multiple relation types show a statistically significant improvement over the current state-of-the-art relational similarity measures.

An important obstacle to the success of the Semantic Web is that the establishment of the semantic relationship is labor-intensive. This paper proposes an automatic semantic relationship discovering approach for constructing the semantic link network. The basic premise of this work is that the semantics of a web page can be reflected by a set of keywords, and the semantic relationship between two web pages can be determined by the semantic relationship between their keyword sets. The approach adopts the data mining algorithms to discover the semantic relationships between keyword sets, and then uses deductive and analogical reasoning to enrich the semantic relationships. The proposed algorithms have been implemented. Experiment shows that the approach is feasible.

Semantic relation plays an important role in knowledge acquisition research. This paper proposes a method of semantic relation acquisition and automatic synthesis based on Wikipedia. First of all, we obtain the three kinds of basic semantic relations from Wikipedia and extend the semantic of concept aiming at the problem of semantic fuzziness in the semantic relation. Then, an automatic synthesis method of semantic relations is proposed based on semantic extension. From the experimental results, this method can effectively extend semantic relation knowledge base through the reasoning of semantic relations.

The goal of Information Retrieval (IR) systems is to satisfy searchers' Information Need (IN). Our research focuses on next-generation IR engines, which can proactively detect, identify, and serve INs without receiving explicit queries. It is essential, therefore, to be able to detect when INs occur. Previous research has established that a realisation of INs physically manifests itself with specific brain activity. With this work we take the next step, showing that monitoring brain activity can lead to accurate predictions of a realisation of IN occurrence. We have conducted experiments whereby twenty-four participants performed a Q/A Task, while their brain activity was being monitored using functional Magnetic Resonance Imaging (fMRI) technology. The questions were selected and developed from the TREC-8 and TREC 2001 Q/A Tracks. We present two methods for predicting the realisation of an IN, i.e. Generalised method (GM) and Personalised method (PM). GM is based on the collective brain activity of all twenty-four participants in a predetermined set of brain regions known to be involved in representing a realisation of INs. PM is unique to each individual and employs a 'Searchlight' analysis to locate brain regions informative for distinguishing when a “specific” user realises an information need. The results of our study show that both methods were able to predict a realisation of an IN (statistically) significantly better than chance. Our results also show that PM (statistically) significantly outperformed GM in terms of prediction accuracy. These encouraging findings make the first fundamental step towards proactive IR engines based on brain signals.

This minitrack addresses a broad range of issues related to the design of the next generation of information retrieval systems, especially related to improving web search effectiveness from the user perspective. The core of this research is how to help the user access and make use of digital data. These issues are of prime interest to researchers, developers, and information managers. The multidisciplinary nature of this emerging area allows us to engage as a community of participants with a wide range of interests, including retrieval design, HCI, information seeking behavior, and information management. Information Retrieval supports the computerized search of large document and digital media collections (millions or billions of items) to select small subsets of those documents relevant to a user's information need. Such algorithms are the basis for internet search engines and question-answering systems. At the same time, we know relatively little about the users who deal with a multi-billion-page Web. Further research is needed to address the user issues related to effectiveness and quality of experience when interacting with search engines. New metrics and methodologies are needed for retrieval evaluation as both the data sets of interest and user expectations grow exponentially. A focus on the user perspective allows us to align the user focus and the system focus in a multi-disciplinary forum that includes theoretical foundations, evaluation measures, methodologies, case studies and user study results. This year in the Information Access & Retrieval MiniTrack we include papers that cover this multidisciplinary approach. One paper, Appropriate Software Components for Mobile End-User Devices Executive Information Systems Up Close and Personalized as an Example, presents design principles for the design of interfaces for mobile devices. Two papers, Building Support for Web Information Gathering Tasks, and Characterizing Queries in Different Search Tasks, explore user behavior related to web search. The first paper examines characteristics of search specific to longer gathering tasks. The second of these papers explores the more general issue of types of tasks for a range of web information needs. The paper, Determinants of Information Channel Choice: The Impact of Task Complexity and Dispositional Character Traits, is a behavioral study of how made channel choice. The final paper, Cobre: A Comparative Book Reader for Los Primeros Libros, presents a novel reader model based on film strip metaphor. 2012 45th Hawaii International Conference on System Sciences

Automatic activation of the semantic network in schizophrenia: evidence from event-related brain potentials

Few-shot object detection has arisen to address the issue of data scarcity due to the long-tail distribution problem. The goal of few-shot object detection is to allow a pre-trained detector to generalize novel objects with few-shot data samples. However, few-shot object detectors misclassify novel objects into pre-trained base classes frequently. Existing methods applied a large margin classifier to address this problem, but they do not work well in data scarcity settings. In this paper, we propose graph convolution network-based semantic relation network to capture the semantic relations for few-shot object detection. Regardless of the amount of data, the semantic relations among object classes remain constant, which can support the classification of novel objects. Semantic relations are trained by the attention-based module adaptively to training data. Graph convolution network updates the object classifier using semantic relations. The object classifier is integrated and trained with the visual features. Through the comparison experiments with Two-stage Fine-tuning Approach (TFA), we observe that our proposed method achieves higher performance on few-shot settings than TFA.