External Semantic Resources Research Articles

CafeteriaFCD Corpus: Food Consumption Data Annotated with Regard to Different Food Semantic Resources.

Besides the numerous studies in the last decade involving food and nutrition data, this domain remains low resourced. Annotated corpuses are very useful tools for researchers and experts of the domain in question, as well as for data scientists for analysis. In this paper, we present the annotation process of food consumption data (recipes) with semantic tags from different semantic resources—Hansard taxonomy, FoodOn ontology, SNOMED CT terminology and the FoodEx2 classification system. FoodBase is an annotated corpus of food entities—recipes—which includes a curated version of 1000 instances, considered a gold standard. In this study, we use the curated version of FoodBase and two different approaches for annotating—the NCBO annotator (for the FoodOn and SNOMED CT annotations) and the semi-automatic StandFood method (for the FoodEx2 annotations). The end result is a new version of the golden standard of the FoodBase corpus, called the CafeteriaFCD (Cafeteria Food Consumption Data) corpus. This corpus contains food consumption data—recipes—annotated with semantic tags from the aforementioned four different external semantic resources. With these annotations, data interoperability is achieved between five semantic resources from different domains. This resource can be further utilized for developing and training different information extraction pipelines using state-of-the-art NLP approaches for tracing knowledge about food safety applications.

Medical Text Classification Based on an Optimized Machine Learning and External Semantic Resource

Automatic classification of texts is a well-known topic in natural language processing (NLP), and it involves categorizing unstructured texts into specific groups. Classification algorithms for a given problem are searched for, as well as the appropriate features to use as input. These models have been used for analysis of data with a large number of sparse dimensions. In medical field, categorization of medical texts is a difficult task because these types of texts contain several terminologies that define medical ideas and words. Medical data also lack proper sentence structure and do not adhere to the standard rules of natural language grammar. The main problem in this classification task is to choose an appropriate representation as input. To solve the representation problem, we propose a new extension model for medical text personification. Our model starts with the preprocessing of medical text. Then, we use external terminology resources to expand the text. After that, we use a combination of different text vector representations. To speed up the process, we try to increase the accuracy while selecting the optimal classification parameters. In this topic, we use an adaptive particle swarm optimization (PSO) algorithm to select the best parameters of a machine learning model. The PubMed, Hallmarks and AIM dataset were used to test our model. Our categorization text model outperforms the competition and provides much higher retrieval accuracy than previous models.

Bi-Gram Term Collocations-based Query Expansion Approach for Improving Arabic Information Retrieval

In the era of information overloading, information retrieval systems are vital applications. Many researchers try to enhance the search results by introducing new methods. Unlike the English language, some languages like Arabic have complex morphological aspects and lack both linguistic and semantic resources. This paper proposes a language-independent semantic-based information retrieval approach, which expands the user query using bi-gram term collocations. The proposed approach has two main contributions. First, the bi-gram term collocations employed to expand the user query are automatically mined from the text corpus, therefore there is no need for an external semantic resource. Second, due to the complexity of the language morphology, the system index is constructed using the corpus words to save the cost and effort of the stemming process. A system prototype for the Arabic language was implemented and evaluated versus the stem-based method. The experimental evaluation has been conducted on the scripts of the Arabic Holy Quran. The evaluation results demonstrate that the proposed system outperforms the stem-based method in terms of precision and recall.

General Knowledge Embedded Image Representation Learning

Image representation learning is a fundamental problem in understanding semantics of images. However, traditional classification-based representation learning methods face the noisy and incomplete problem of the supervisory labels. In this paper, we propose a general knowledge base embedded image representation learning approach, which uses general knowledge graph, which is a multitype relational knowledge graph consisting of human commonsense beyond image space, as external semantic resource to capture the relations of concepts in image representation learning. A relational regularized regression CNN (R $^3$ CNN) model is designed to jointly optimize the image representation learning problem and knowledge graph embedding problem. In this manner, the learnt representation can capture not only labeled tags but also related concepts of images, which involves more precise and complete semantics. Comprehensive experiments are conducted to investigate the effectiveness and transferability of our approach in tag prediction task, zero-shot tag inference task, and content-based image retrieval task. The experimental results demonstrate that the proposed approach performs significantly better than the existing representation learning methods. Finally, observation of the learnt relations show that our approach can somehow refine the knowledge base to describe images and label the images with structured tags.

Exogenous approach to improve topic segmentation

Purpose – Topic segmentation is one of the active research fields in natural language processing. Also, many topic segmenters have been proposed. However, the current challenge of researchers is the improvement of these segmenters by using external resources. Therefore, the purpose of this paper is to integrate study and evaluate a new external semantic resource in topic segmentation. Design/methodology/approach – New topic segmenters (TSS-Onto and TSB-Onto) are proposed based on the two well-known segmenters C99 and TextTiling. The proposed segmenters integrate semantic knowledge to the segmentation process by using a domain ontology as an external resource. Subsequently, an evaluation is made to study the effect of this resource on the quality of topic segmentation along with a comparative study with related works. Findings – Based on this study, the authors showed that adding semantic knowledge, which is extracted from a domain ontology, improves the quality of topic segmentation. Moreover, TSS-Ont outperforms TSB-Ont in terms of quality of topic segmentation. Research limitations/implications – The main limitation of this study is the used test corpus for the evaluation which is not a benchmark. However, we used a collection of scientific papers from well-known digital libraries (ArXiv and ACM). Practical implications – The proposed topic segmenters can be useful in different NLP applications such as information retrieval and text summarizing. Originality/value – The primary original contribution of this paper is the improvement of topic segmentation based on semantic knowledge. This knowledge is extracted from an ontological external resource.

Automatic medical image multilingual annotation via a medical social network

Medical social networking sites enabled multimedia content sharing in large volumes, by allowing physicians and patients to upload their medical images. These images are diagnosed and commented, in different languages, by several specialists instantly. Moreover, it is necessary to employ new techniques, in order to automatically extract information and analyze knowledge from the huge number of comments expressing specialist’s analyzes and recommendations. For this reason, we propose a terms-based method in order to extract the relevant terms and words which can describe the medical image. Furthermore, significant extracted terms and keywords will be used later to index medical images, in order to facilitate their search through the social network site. In fact, we need to take account that existing comments are expressed in different languages. So, it is essential to implement a multilingual indexation method to eliminate the ambiguity which will be the cause of the effectiveness’s reduction of the search function. In order to palliate this situation, we propose a multilingual mixed approach which concentrates on algorithms based on statistical methods and external multilingual semantic resources, in order to handle and to cover different languages. The use of external resources, such as semantic multilingual thesaurus, can improve the efficiency of the indexing process. The proposed method can be applied in different languages. Our study is validated by a set of experiments and a comparison study with some existing approaches in literature. Experimental results have indicated that the proposed system has a superior performance compared to other systems. Finally, we need also to verify whether the system is considered by the specialists as a potential aid. We evaluate its impact, by inquiring the specialists about the degree of confidence in our system. By analyzing the obtained results, we can argue that the proposed system presented a high acceptance and viability rate regarding the specialists’ interests in the annotation practice domain.

A medical collaboration network for medical image analysis

Nowadays, patients are often in a hurry to know their analysis and concise explanations their medical images pending the doctor’s decision. Most of the time, doctors can make mistakes leading to unpredictable damage in patients. In order to minimize medical errors by fostering collaboration between physicians and/or patients, we propose in this paper, as a first contribution, a medical social network destined to gather patients’ medical images and physicians’ annotations expressing their medical reviews and advice. As the volume of comments is very important, analysis of opinions becomes an impossible task and requires automatic processing to extract relevant information collected from the comments of specialists. For this purpose, we propose a second contribution of producing summaries of comments containing most current conditions and relevant words prescribed by doctors. Furthermore, this extracted information will present a new and robust input for image indexation enhanced methods. In fact, significant extracted terms will be used later to index images in order to facilitate their search through the underlying social network. To overcome the above challenges, we propose an approach which focuses on algorithms mainly based on statistical methods and external semantic resources destined to filter selected extracts information.

The joint student response analysis and recognizing textual entailment challenge: making sense of student responses in educational applications

We present the results of the joint student response analysis (SRA) and 8th recognizing textual entailment challenge. The goal of this challenge was to bring together researchers from the educational natural language processing and computational semantics communities. The goal of the SRA task is to assess student responses to questions in the science domain, focusing on correctness and completeness of the response content. Nine teams took part in the challenge, submitting a total of 18 runs using methods and features adapted from previous research on automated short answer grading, recognizing textual entailment and semantic textual similarity. We provide an extended analysis of the results focusing on the impact of evaluation metrics, application scenarios and the methods and features used by the participants. We conclude that additional research is required to be able to leverage syntactic dependency features and external semantic resources for this task, possibly due to limited coverage of scientific domains in existing resources. However, each of three approaches to using features and models adjusted to application scenarios achieved better system performance, meriting further investigation by the research community.

Test-bed building process for context-aware peer-to-peer information retrieval evaluation

With the rapid growth of information rate in the web, it is of paramount importance to develop scalable information retrieval approaches. These approaches are based on distributed information retrieval systems. Likewise, the emergence of contextual information retrieval has introduced the research personalisation which attempts to reduce the research ambiguity and to return most appropriate information to the user. Therefore, it seems a compelling issue, to implement techniques related to contextual peer-to-peer information retrieval (P2P-IR) to better exploit the personalisation of information in order to achieve a more efficient access to data. In this respect, evaluating these approaches in contextual P2P-IR is a crucial step. Indeed, to the best of our knowledge, there is no available test-beds dedicated to the evaluation of contextual P2P-IR. In particular, we propose, two methods. The first is based on existing collections that are enriched with external semantic resources. The second offers the possibility to build test-beds from multiple sources data.

Addressing semantic heterogeneity through multiple knowledge base assisted merging of domain-specific ontologies

With the development of the Semantic Web (SW), the creation of ontologies to formally conceptualize our understanding of various domains has widely increased in number. However, the conceptual and terminological differences (a.k.a semantic heterogeneity problem) between ontologies form a major limiting factor towards their use/reuse and full adoption in practical settings. A key solution to addressing this problem can be through identifying semantic correspondences between the entities (including concepts, relations, and instances) of heterogeneous ontologies, and consequently achieving interoperability between them. This process is also known as ontology alignment. The output of this process can be further exploited to merge ontologies into a single coherent ontology. Indeed, this is widely regarded as a crucial, yet difficult task, specifically when dealing with heavyweight ontologies that consist of hundreds of thousands of concepts. To address this issue, various ontology merging approaches have been proposed. These approaches can be classified into three categories: single-strategy-based approaches, multiple-strategy-based approaches, and approaches based on exploiting external semantic resources. In this paper, we first discuss the strengths and limitations of each of these approaches, and then present our framework for addressing the semantic heterogeneity problem through merging domain-specific ontologies based on multiple external semantic resources. The novelty of the proposed approach is mainly based on employing knowledge represented by multiple external resources (knowledge bases in our work) to make aggregated decisions on the semantic correspondences between the entities of heterogeneous ontologies. Other important issues that we attempt to tackle in the proposed framework are: (i) Identifying and handling inconsistency of semantic relations between the ontology concepts and, (ii) Handling the issue of missing background knowledge (such as concepts and instances) in the exploited knowledge bases by utilizing an integrated statistical and semantic technique. Additionally, the proposed solution soundly enriches the knowledge bases with missing background knowledge, and thus enables the reuse of the newly obtained knowledge in future ontology merging tasks. To validate our proposal, we tested the framework using the OAEI 2009 benchmark and compared the produced results with state-of-the-art syntactic and semantic based systems. In addition, we utilized the proposed techniques to merge three heavyweight ontologies from the environmental domain.

A medical social network for physicians’ annotations posting and summarization

Patients are often anxious to quickly discover reliable analysis and concise explanation of their medical images while waiting for the physician decision. The fact of making important choices individually in his own corner may lead the physician to commit errors leading to malpractices and consequently to unforeseeable damages. In order to minimize medical errors by fostering collaboration between physicians and/or patients, we propose in this paper, as a first contribution, a medical social network destined to gather patients’ medical images and physicians’ annotations expressing their medical reviews and advices. The need, to automatically extract information and analyze opinions, becomes obviously a requirement due to the huge number of comments expressing specialists’ recommendations and/or remarks. For this purpose, we propose a second contribution consisting of providing a kind of comments’ summary which extracts the major current terms and relevant words existing on physicians’ reports. Furthermore, this extracted information will present a new and robust input for image indexation enhanced methods. In fact, significant extracted terms will be used later to index images in order to facilitate their search through the underlying social network. To overcome the above challenges, we propose an approach which focuses on algorithms mainly based on statistical methods and external semantic resources destined to filter selected extracted information.

Indexing Medical Images based on Collaborative Experts Reports

A patient is often willing to quickly get, from his physician, reliable analysis and concise explanation according to provided linked medical images. The fact of making choices individually by the patient's physician may lead to malpractices and consequently generates unforeseeable damages. The Institute of Medicine of the National Sciences Academy(IMNAS) in USA published a study estimating that up to 98,000 hospital deathseach year can be attributed to medical malpractice [1]. Moreover, physician, in charge of medical image analysis, might be unavailable at the right time, which may complicate the patient's state. The goal of this paper is to provide to physicians and patients, a social network that permits to foster cooperation and to overcome the problem of unavailability of doctors on site any time. Therefore, patients can submit their medical images to be diagnosed and commented by several experts instantly. Consequently, the need to process opinions and to extract information automatically from the proposed social network became a necessity due to the huge number of comments expressing specialist's reviews. For this reason, we propose a kind of comments' summary keywords-based method which extracts the major current terms and relevant words existing on physicians' annotations. The extracted keywords will present a new and robust method for image indexation. In fact, significant extracted terms will be used later to index images in order to facilitate their discovery for any appropriate use. To overcome this challenge, we propose our Terminology Extraction of Annotation (TEA) mixed approach which focuses on algorithms mainly based on statistical methods and on external semantic resources.