Semantic Representation Model Research Articles

Question Answering over Knowledge Bases

Question answering over knowledge bases is a challenging task for next-generation search engines. The core of this task is to understand the meaning of questions and translate them into structured language-based queries. Previous research has focused on a specific knowledge base with a constrained domain, but with the increase in the size and domain of existing knowledge bases, fulfilling this aim is even more challenging. This article introduces the mainstream methods for question answering over knowledge bases, describing typical semantic meaning representation models and state-of-the-art systems for converting questions to predefined logical forms. It also puts a particular focus on the approaches for question answering over a large-scale knowledge base and multiple heterogeneous knowledge bases.

Recognition during recall failure: Semantic feature matching as a mechanism for recognition of semantic cues when recall fails.

Research suggests that a feature-matching process underlies cue familiarity-detection when cued recall with graphemic cues fails. When a test cue (e.g., potchbork) overlaps in graphemic features with multiple unrecalled studied items (e.g., patchwork, pitchfork, pocketbook, pullcork), higher cue familiarity ratings are given during recall failure of all of the targets than when the cue overlaps in graphemic features with only one studied target and that target fails to be recalled (e.g., patchwork). The present study used semantic feature production norms (McRae et al., Behavior Research Methods, Instruments, & Computers, 37, 547-559, 2005) to examine whether the same holds true when the cues are semantic in nature (e.g., jaguar is used to cue cheetah). Indeed, test cues (e.g., cedar) that overlapped in semantic features (e.g., a_tree, has_bark, etc.) with four unretrieved studied items (e.g., birch, oak, pine, willow) received higher cue familiarity ratings during recall failure than test cues that overlapped in semantic features with only two (also unretrieved) studied items (e.g., birch, oak), which in turn received higher familiarity ratings during recall failure than cues that did not overlap in semantic features with any studied items. These findings suggest that the feature-matching theory of recognition during recall failure can accommodate recognition of semantic cues during recall failure, providing a potential mechanism for conceptually-based forms of cue recognition during target retrieval failure. They also provide converging evidence for the existence of the semantic features envisaged in feature-based models of semantic knowledge representation and for those more concretely specified by the production norms of McRae et al. (Behavior Research Methods, Instruments, & Computers, 37, 547-559, 2005).

A Framework to Normalize Ontology Representation for Stable Measurement

Ontology measurement is an important challenge in the field of knowledge management in order to manage the development of ontology based systems and reduce the risk of project failure. Effective ontology measurement is the precondition on which the meaningful and useful ontology evaluation can be made. We propose a framework to normalize representation of ontologies for their stable measurement, where the semantic enriched representation model (SERM) is proposed as the unique representation for ontologies. By the normalization framework, we provide a four-step procedure to extract ontology entities and calculate measures based on SERM model. Both the theoretical analysis and the experimental results show that our framework is effective and useful to perform stable ontology measurement. It is suitable to measure more expressive ontologies. This framework enables users to perform automatic ontology measurement without much expertise knowledge about ontology programming and reasoning.

A novel approach for automatic extraction of semantic data about football transfer in sport news

Purpose – The purpose of this paper is to propose an automatic method to generate semantic annotations of football transfer in the news. The current automatic news integration systems on the Web are constantly faced with the challenge of diversity, heterogeneity of sources. The approaches for information representation and storage based on syntax have some certain limitations in news searching, sorting, organizing and linking it appropriately. The models of semantic representation are promising to be the key to solving these problems. Design/methodology/approach – The approach of the author leverages Semantic Web technologies to improve the performance of detection of hidden annotations in the news. The paper proposes an automatic method to generate semantic annotations based on named entity recognition and rule-based information extraction. The authors have built a domain ontology and knowledge base integrated with the knowledge and information management (KIM) platform to implement the former task (name...

Modeling semantic knowledge structures for creative problem solving: Studies on expressing concepts, categories, associations, goals and context

This paper presents a model for semantic network representation. According to the model, the main purpose of a semantic network is to help to correctly and quickly understand the features and structure of the solutions, and then make reliable predictions about their outcomes and rewards. These objectives are achieved under constrains like limited resources (e.g., memory size and access), time limitations, and variations of solution characteristics. The paper summarizes the elements of the model and presents a set of properties that describe the effectiveness of semantic networks in creative problem solving, including design. Six examples (based on three case studies from the related literature and three experimental studies conducted by the authors) discuss the model elements, characteristics, and properties.

WYSIWYM – Integrated visualization, exploration and authoring of semantically enriched un-structured content

The Semantic Web and Linked Data gained traction in the last years. However, the majority of information still is contained in unstructured documents. This can also not be expected to change, since text, images and videos are the natural way how humans interact with information. Semantic structuring on the other hand enables the (semi-)automatic integration, repurposing, rearrangement of information. NLP technologies and formalisms for the integrated representation of unstructured and semantic content (such as RDFa and Microdata) aim at bridging this semantic gap. However, in order for humans to truly benefit from this integration, we need ways to author, visualize and explore unstructured and semantically enriched content in an integrated manner. In this paper, we present the WYSIWYM (What You See is What You Mean) concept, which addresses this issue and formalizes the binding between semantic representation models and UI elements for authoring, visualizing and exploration. With RDFaCE, Pharmer and conTEXT we present and evaluate three complementary showcases implementing the WYSIWYM concept for different application domains.

LCA-oriented semantic representation for the product life cycle

In order to complete a life cycle assessment (LCA) study of the product, each activity interacting with the environment during the product life cycle should be given an explicit description, namely an LCA-oriented representation for the product life cycle should be constructed. A complex functional product usually consists of many parts made of different materials and its LCA-oriented life cycle modeling involves many complex semantic relationships. In this paper, a new LCA-oriented and ontology-based semantic representation model and methodology for the product life cycle are proposed. First, the concepts of processes and flows, and the semantic relationships among processes, and between processes and flows are analyzed in detail. The ontology classes of processes and flows are defined using the Web Ontology Language (OWL). Then, an LCA-oriented semantic concept model for the product life cycle is presented. Based on the proposed semantic representation model, all processes, flows, and the relationships among them can be represented as a Resource Description Framework (RDF) graph in which each node is an instance tagged by an ontology class. A formalization of lifecycle processes on flows is provided, which can be encoded with Semantic Web Rule Language (SWRL) and formed into a knowledge rule base. In addition, a semantic query method for the life cycle inventory of a product is proposed. Finally, an implementation framework and an example of the semantic representation for a ball bearing's life cycle are provided.

Resolving the Semantics of Vietnamese Questions in VNewsQA/ICT System

Recently we have built a VNewsQA/ICT system which can read the titles of Vietnamese news in the domain of information and communication technology, then process and use them to answer the Vietnamese questions of users. The architecture of VNewsQA/ICT system has two main components: 1) the first component treats the simple Vietnamese sentences as its natural language textual data which is used to answer the user’s questions; 2) the second component resolves the semantics of Vietnamese questions which query the system. This paper introduces a semantic representation model and a processing model to revolve the Vietnamese questions in VNewsQA/ICT system. These semantic representation and processing models are able to resolve the semantics of eight Vietnamese question classes which are used in our system.

A Generic Implementation Framework for Measuring Ontology-Based Information

AbstractAs a knowledge representation tool, ontologies have been widely applied in many fields such as knowledge management and information integration, etc. Ontology measurement is an important challenge in the field of knowledge management in order to manage the development of ontology based systems and reduce the risk of project failure. This paper proposes a generic implementation framework for stable semantic ontology measurement. Through this framework, an ontology will be measured according to its semantic enriched representation model (SERM). The SERM model of an ontology can be used for stably measuring the semantics of the ontology. Then ontology metrics are integrated into the framework to measure candidate ontologies according to its SERM model. The related experiments are made to show that the framework can effectively measure the semantics of ontologies.

Research on SOM-Based Query Reformulation in Emergency Decision

The efficiency and accuracy of professional retrieval are closely related to semantic representation model in professional field. Representing retrieval requirement accurately is very important to guaranteeing the accuracy of retrieval. In case of professional emergency field, a query reformulation model used to clearing and improving user retrieval requirement is researched. Constructing a latent semantic word space of emergency field, semantic features are clustered by using SOM, and CI index using to determining the optimal cluster boundary is proposed. On this basis, a new query reformulation method is designed. The effectiveness of model is verified by experiment.

A Leak Detection Method Based on Semantic Knowledge Representation and Derivation Model

Prevention from the leak of release information is a major challenge in public release information security issues. The derivation relation inherent in the information is the key to leak. To address the problem, a leak detection method based on semantic knowledge representation and derivation model is presented within two detections over the release information. Firstly, semantic knowledge of a sentence can be represented in the frame-based hierarchy through semantic and syntax analyses. Base on this, leaks in some ways can be detected, such as by enclosing information that need to be confidential (general secret information) directly, by using the substitution of synonym or restatement of secret information. Secondly, the derivation model is constructed through the hierarchy and derivation relations implicated in the information. This model is tailored to detect leaks caused by information derivation. Finally, we also report on the theory and experiment analysis. The result is satisfying.

George A. Miller

George Armitage Miller died on July 22, 2012, at the age of ninety-two. He led a rich life full of accomplishments in the three areas of activity that he had chosen as a young man: psychology, writing, and golf. Miller was not only a witness but a key player in the major paradigm shift of the 20th century that came to be known as the cognitive revolution. Incredible as it may seem today, his teachers at Harvard followed the behaviorist dogma and recognized neither the autonomy nor the significance of the human mind. It took two courageous young scientists—George Miller and Jerome Bruner—to assert, each in their own domain of investigation, that the mind is a worthwhile subject of study. They started out by teaching a course boldly entitled “Cognition” and eventually established the Center for Cognitive Studies, ultimately making behaviorism obsolete. Miller drew an analogy between the human mind and a computer, noting that both store and process huge amounts of information. At the same time, human shortterm memory is limited, as his most celebrated paper on the “Magical Number Seven” demonstrates (Miller 1956/1994). Miller showed that chunking information into meaningful units helps recall, though the number of units that can be memorized seems to hover around seven. For example, U.S. telephone numbers are broken down into three groups of three, three, and four digits (area code, local exchange, and individual number). Chunk parsers (Abney 1991) build on the idea that sentence processing proceeds in phrases, reflected in prosodic patterns. Among our cognitive faculties, it was language in particular that fascinated George, a gifted writer. One attraction was that linguistic behavior could be observed, tested, and evaluated quantitatively with the experimental paradigms available to psycholinguists at a time when brain imaging techniques had not yet been developed. The rules of language, with their recursive aspects, could be seen as a kind of program. Although he collaborated with Noam Chomsky on the formal aspects of language, Miller in later life harbored a suspicion of highly abstract theories of syntax. His interest lay primarily in the lexicon, not only because of his authorial love of words, but also because of its size, open-endedness, and dynamic aspects. Moreover, the growth of children’s lexicons offered a window into their cognitive development. Miller is probably best known to readers of Computational Linguistics for his creation of the large lexical database WordNet (Miller 1995). WordNet’s use as a resource for natural language processing was in fact unintended, and its rapid adoption by the NLP community came as a surprise. George was interested in human semantic organization and wanted to test the then-fashionable concept of semantic networks, which allowed for plausible and elegant models of semantic representation and seemed supported by experiments testing lexical access and retrieval (Collins and Quillian 1969). Miller wondered whether a semantic network could in fact be built for the bulk of the English lexicon. In the mid 1980s, he recruited a group of colleagues, students, and his wife Kitty and, without much further instruction, asked them to cluster nouns, verbs, and

Document clustering using the LSI subspace signature model

We describe the latent semantic indexing subspace signature model (LSISSM) for semantic content representation of unstructured text. Grounded on singular value decomposition, the model represents terms and documents by the distribution signatures of their statistical contribution across the top‐ranking latent concept dimensions. LSISSM matches term signatures with document signatures according to their mapping coherence between latent semantic indexing (LSI) term subspace and LSI document subspace. LSISSM does feature reduction and finds a low‐rank approximation of scalable and sparse term‐document matrices. Experiments demonstrate that this approach significantly improves the performance of major clustering algorithms such as standard K‐means and self‐organizing maps compared with the vector space model and the traditional LSI model. The unique contribution ranking mechanism in LSISSM also improves the initialization of standard K‐means compared with random seeding procedure, which sometimes causes low efficiency and effectiveness of clustering. A two‐stage initialization strategy based on LSISSM significantly reduces the running time of standard K‐means procedures.

A semantic representation model for design rationale of products

Design rationale (DR) is crucial information in product design decision support, design analysis and design reuse. In this paper, based on the Issue-based Information System (IBIS) model, a new ontology-based semantic representation model for DR information; the integrated issue, solution, artifact and argument (ISAA) model; is proposed. The ISAA model introduces the ontology-based semantic representation mode to the DR representation and expands the concept elements of IBIS. The class of concept elements and the semantic relationships among them are defined by Web Ontology Language (OWL). The axioms and rules which are used to reason and analyze DR are defined and encoded with Semantic Web Rule Language (SWRL), which enrich the semantic relations defined by OWL. The ISAA model represents the directed graph of IBIS to the Resource Description Framework (RDF) graph and serializes to an RDF/XML document which lays the foundation for retrieving and reasoning semantic information of DR. A semantic annotator integrating with the visual product design model was developed, by which the discrete information of thinking is captured and abstracted to a conceptual representation of the ISAA model. Finally, an example of DR representation for the spring operating mechanism of a high-voltage circuit breaker product is given.

Identifying the semantic orientation of terms using S-HAL for sentiment analysis

Sentiment analysis continues to be a most important research problem due to its abundant applications. Identifying the semantic orientation of subjective terms (words or phrases) is a fundamental task for sentiment analysis. In this paper, we propose a new method for identifying the semantic orientation of subjective terms to perform sentiment analysis. The method takes a classification approach that is based on a novel semantic orientation representation model called S-HAL (Sentiment Hyperspace Analogue to Language). S-HAL basically produces a set of weighted features based on surrounding words, and characterizes the semantic orientation information of words via a specific feature space. Because the method incorporates the idea underlying HAL and the hypothesis verified by the method of semantic orientation inference from pointwise mutual information (SO-PMI), it can quickly and accurately identify the semantic orientation of terms without the use of an Internet search engine. The results of an empirical evaluation show that our method outperforms other known methods.

Distinctive Semantic Feature Loss in Alzheimer’s Disease

Event Abstract Back to Event Distinctive Semantic Feature Loss in Alzheimer’s Disease Kieran J. Flanagan1*, David A. Copland1, 2, Helen J. Chenery3, Gerard J. Byrne4 and Anthony J. Angwin1 1 University of Queensland, School of Health and Rehabilitation Sciences, Australia 2 University of Queensland, Centre for Clinical Research, Australia 3 University of Queensland, Centre for Clinical Research, Australia 4 University of Queensland, School of Medicine, Australia The degraded storage account is frequently used to explain anomia in Alzheimer’s disease (AD). This account asserts that anomia in AD is caused by the progressive loss of semantic features with distinctive semantic features more vulnerable to loss than non-distinctive features. Supporting studies have been criticized for their over reliance on verbal tasks with high cognitive demands which may confound their findings. The current study used a novel version of the yes-no recognition task that controlled for the cognitive demands of the task and used picture stimuli to compare the processing of distinctive and non-distinctive features in participants with AD and healthy controls. Eleven participants with AD and 24 control participants matched for age, sex and education were recruited. Participants were required to learn and series of pictures in a study phase and indicate which pictures they had seen before from a larger set of pictures in a test phase. Pictures in the test phase were either identical, semantically related or unrelated to items in the study phase or altered by a distinctive or non-distinctive semantic feature. Evidence was found to support the differential processing of distinctive and non-distinctive features in AD with the accuracy of performance of participants with AD decreasing relative to control participants when distinctive features but not non-distinctive features were manipulated between study and test phased. These findings support the degraded storage hypothesis of anomia in AD and are discussed with respect to current models of semantic representation. Acknowledgements Alison Argo, Elizabeth Arnold, Claire Flanagan, Michael Humphreys. Copland was supported by a NHMRC Clinical Career Development Award and an ARC Future Fellowship. Keywords: semantic features, Alzheimer’s disease, Degraded access, Degraded storage, memory and learning task Conference: ACNS-2012 Australasian Cognitive Neuroscience Conference, Brisbane, Australia, 29 Nov - 2 Dec, 2012. Presentation Type: Oral Presentation Topic: Language Citation: Flanagan KJ, Copland DA, Chenery HJ, Byrne GJ and Angwin AJ (2012). Distinctive Semantic Feature Loss in Alzheimer’s Disease. Conference Abstract: ACNS-2012 Australasian Cognitive Neuroscience Conference. doi: 10.3389/conf.fnhum.2012.208.00199 Copyright: The abstracts in this collection have not been subject to any Frontiers peer review or checks, and are not endorsed by Frontiers. They are made available through the Frontiers publishing platform as a service to conference organizers and presenters. The copyright in the individual abstracts is owned by the author of each abstract or his/her employer unless otherwise stated. Each abstract, as well as the collection of abstracts, are published under a Creative Commons CC-BY 4.0 (attribution) licence (https://creativecommons.org/licenses/by/4.0/) and may thus be reproduced, translated, adapted and be the subject of derivative works provided the authors and Frontiers are attributed. For Frontiers’ terms and conditions please see https://www.frontiersin.org/legal/terms-and-conditions. Received: 25 Oct 2012; Published Online: 27 Nov 2012. * Correspondence: Mr. Kieran J Flanagan, University of Queensland, School of Health and Rehabilitation Sciences, Brisbane, Queensland, 4072, Australia, k.flanagan@uq.edu.au Login Required This action requires you to be registered with Frontiers and logged in. To register or login click here. Abstract Info Abstract The Authors in Frontiers Kieran J Flanagan David A Copland Helen J Chenery Gerard J Byrne Anthony J Angwin Google Kieran J Flanagan David A Copland Helen J Chenery Gerard J Byrne Anthony J Angwin Google Scholar Kieran J Flanagan David A Copland Helen J Chenery Gerard J Byrne Anthony J Angwin PubMed Kieran J Flanagan David A Copland Helen J Chenery Gerard J Byrne Anthony J Angwin Related Article in Frontiers Google Scholar PubMed Abstract Close Back to top Javascript is disabled. Please enable Javascript in your browser settings in order to see all the content on this page.

Automatic Construction of Entity Semantic Representation Model Based on Dependency Analysis

The entity semantic representation model (ESRM), which considers an entity as a set of attributes and corresponding values, is very useful for various applications. This paper proposes an approach for extracting new attributes and values from related unstructured documents. In our approach, the extraction process is formulated as the sequence labeling task. According to the predefined entity structure, the labeled data for training annotator are achieved automatically. The CRFs based annotator is trained to annotate the sentence which maybe contains the new attributes and values. And then, in terms of a decision process with scoring algorithm, new attributes and values are identified and fill into the predefined entity representation model. The experiments show that the proposed method improves the performance of extraction with a higher accuracy.

At the Edge of Semantic Space: The Breakdown of Coherent Concepts in Semantic Dementia Is Constrained by Typicality and Severity but Not Modality

Hub-and-spoke models of semantic representation suggest that coherent concepts are formed from the integration of multiple, modality-specific information sources with additional modality-invariant representations-most likely stored in the ventrolateral anterior temporal lobe (vATL). As well as providing the necessary computational mechanisms for the complexities of feature integration, these modality-invariant representations also license a key aspect of semantic memory-semantic-based generalization. Semantic dementia allows us to investigate this aspect of conceptual knowledge because (a) the patients have a selective and progressive semantic degradation and (b) this is associated with profound ventrolateral ATL atrophy. Specifically, the boundaries between concepts become degraded in semantic dementia and, when tested using the appropriate materials, the patients make simultaneous under- and overgeneralization errors. We found that the rate of these errors were a function of typicality and pseudotypicality of the items as well as the severity of the patients' semantic impairment. Following the modality-invariant nature of the vATL hub representation, we also confirmed that the patients were impaired on both verbal- and picture-based versions of the same task.

“W” is for bath: Can associative errors be cued?

Semantic aphasia (SA) refers to a condition in which the control processes associated with the use of semantic information become compromised. This condition compromises patients’ abilities to accurately name pictures, and they produce semantic errors in the form of co-ordinate items, such as “shower” for BATH. Previous research has demonstrated that these patients are sensitive to phonemic cues during picture naming, whether they promote the correct response (e.g., /b/) or the incorrect semantically related response (e.g., /sh/). A similar pattern is observed in normal participants when asked to perform tempo picture naming, in which the timing constraints undermine semantic control processes. SA patients are also known to produce associative errors in picture naming, such as “water” for BATH. In this study, we extended previous work on phonemic cueing in SA patients and in normal participants in two ways: firstly, by using associative miscues to promote associative errors (e.g., /w/), and secondly, to confirm miscueing effects still hold when assessed relative to a neutral condition of an unrelated phoneme rather a simple beep. The results revealed that associative miscues are effective in reducing accuracy and promoting semantic errors in SA patients. Correlations between associative cueing effects and executive tests showed that the impact of associative miscues was more pronounced in those with greater semantic control impairment. Associative miscueing was also seen for normal participants during tempo picture naming, including a latency cost. Both the associative and also the co-ordinate miscueing effects were still apparent when the neutral condition consisted of an unrelated phoneme. The implications of these results for models of speech production and semantic representation are outlined.

Generating Text from Functional Brain Images

Recent work has shown that it is possible to take brain images acquired during viewing of a scene and reconstruct an approximation of the scene from those images. Here we show that it is also possible to generate text about the mental content reflected in brain images. We began with images collected as participants read names of concrete items (e.g., “Apartment’’) while also seeing line drawings of the item named. We built a model of the mental semantic representation of concrete concepts from text data and learned to map aspects of such representation to patterns of activation in the corresponding brain image. In order to validate this mapping, without accessing information about the items viewed for left-out individual brain images, we were able to generate from each one a collection of semantically pertinent words (e.g., “door,” “window” for “Apartment’’). Furthermore, we show that the ability to generate such words allows us to perform a classification task and thus validate our method quantitatively.