Pub Date : 2011-06-28DOI: 10.1109/STAIR.2011.5995783
Syarifah Bahiyah Rahayu, S. Noah
Semantic annotation represents a metadata of the document based on domain ontology. The purpose of this paper is to present semantic similarity document annotation ranking framework given a user's query. The framework features related concepts inclusion and applies appropriate weighting functions. Our aim is to rank and score semantic document annotation based on document richness. We also compare our approach with other methods using a research prototype retrieval engine, PicoDoc. The system framework of PicoDoc is based on OCAS2008 ontology. In this experiment, we are using a real-life dataset from news article corpus from ABC and BBC. The experiment shows promising results in retrieving related information using the proposed framework.
{"title":"Annotated document: Scoring and ranking method","authors":"Syarifah Bahiyah Rahayu, S. Noah","doi":"10.1109/STAIR.2011.5995783","DOIUrl":"https://doi.org/10.1109/STAIR.2011.5995783","url":null,"abstract":"Semantic annotation represents a metadata of the document based on domain ontology. The purpose of this paper is to present semantic similarity document annotation ranking framework given a user's query. The framework features related concepts inclusion and applies appropriate weighting functions. Our aim is to rank and score semantic document annotation based on document richness. We also compare our approach with other methods using a research prototype retrieval engine, PicoDoc. The system framework of PicoDoc is based on OCAS2008 ontology. In this experiment, we are using a real-life dataset from news article corpus from ABC and BBC. The experiment shows promising results in retrieving related information using the proposed framework.","PeriodicalId":376671,"journal":{"name":"2011 International Conference on Semantic Technology and Information Retrieval","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121927746","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2011-06-28DOI: 10.1109/STAIR.2011.5995764
Kasturi Dewi Varathan, T. Sembok, N. Omar, R. A. Kadir
The representation of document content is very important factors in retrieval process. The failure to create a good knowledge representation will definitely lead to failure in terms of its retrieval no matter how good the retrieval engine is. Therefore, this research focused on creating a reliable knowledge representation for our retrieval engine. We are using skolem to capture the information conveyed by multiple text documents and used skolem as an index language. This research also focuses on utilizing the skolem index as its knowledge representation in its question answering system. The system is capable of retrieving the answer as well as states the exact document in which the answer is derived from.
{"title":"Retrieving answers from multiple documents using semantic skolem indexing","authors":"Kasturi Dewi Varathan, T. Sembok, N. Omar, R. A. Kadir","doi":"10.1109/STAIR.2011.5995764","DOIUrl":"https://doi.org/10.1109/STAIR.2011.5995764","url":null,"abstract":"The representation of document content is very important factors in retrieval process. The failure to create a good knowledge representation will definitely lead to failure in terms of its retrieval no matter how good the retrieval engine is. Therefore, this research focused on creating a reliable knowledge representation for our retrieval engine. We are using skolem to capture the information conveyed by multiple text documents and used skolem as an index language. This research also focuses on utilizing the skolem index as its knowledge representation in its question answering system. The system is capable of retrieving the answer as well as states the exact document in which the answer is derived from.","PeriodicalId":376671,"journal":{"name":"2011 International Conference on Semantic Technology and Information Retrieval","volume":"84 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122938844","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2011-06-28DOI: 10.1109/STAIR.2011.5995797
Mohd Juzaiddin Abd. Aziz, S. Noah, M. P. Hamzah
This paper not considering how to determine antecedents with its anaphor, but to discuss how to determine the anaphoric word. Anaphoric word determination is important process needs in anaphora resolution. In Malay language there is a word that can be used in three conditions; human referral, other than human referral and not referral word. The word is “nya”. The usage of word “nya” can be trace based on semantic knowledge of word that combines with word “nya”. A novel approach is proposed to identify such uses of “nya”. The propose approach is semantic knowledge that focus on classification of words before “nya”. There are three type of word involve in this determination process. The types are nouns, verb and “kata tugas”. There are classes that have been identified for each type of word. These classes are 16 classes to determine pronoun, six classes for referral word and other than those classes are for not referral word. The experiment has been executed using 60 text news from Berita Harian that consist of 385 word “nya” with 278 “nya” as human referral, 35 “nya” as other than human referral and 72 “nya” not referral word. The result shows that the rules are acceptable. The precision for human referral, other than human referral and non referral word are 0.960, 0.824 and 0.627 respectively. Where else recall for pronoun, referral word, and non-referral word are 0.863, 0.412 and 0.973.
{"title":"“nya” as anaphoric word: A proposed solution","authors":"Mohd Juzaiddin Abd. Aziz, S. Noah, M. P. Hamzah","doi":"10.1109/STAIR.2011.5995797","DOIUrl":"https://doi.org/10.1109/STAIR.2011.5995797","url":null,"abstract":"This paper not considering how to determine antecedents with its anaphor, but to discuss how to determine the anaphoric word. Anaphoric word determination is important process needs in anaphora resolution. In Malay language there is a word that can be used in three conditions; human referral, other than human referral and not referral word. The word is “nya”. The usage of word “nya” can be trace based on semantic knowledge of word that combines with word “nya”. A novel approach is proposed to identify such uses of “nya”. The propose approach is semantic knowledge that focus on classification of words before “nya”. There are three type of word involve in this determination process. The types are nouns, verb and “kata tugas”. There are classes that have been identified for each type of word. These classes are 16 classes to determine pronoun, six classes for referral word and other than those classes are for not referral word. The experiment has been executed using 60 text news from Berita Harian that consist of 385 word “nya” with 278 “nya” as human referral, 35 “nya” as other than human referral and 72 “nya” not referral word. The result shows that the rules are acceptable. The precision for human referral, other than human referral and non referral word are 0.960, 0.824 and 0.627 respectively. Where else recall for pronoun, referral word, and non-referral word are 0.863, 0.412 and 0.973.","PeriodicalId":376671,"journal":{"name":"2011 International Conference on Semantic Technology and Information Retrieval","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116292660","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2011-06-28DOI: 10.1109/STAIR.2011.5995771
Mehdi Rohaninezhad, N. Omar
Precisiated natural language is a new paradigm in soft computing based on information granulation. This paradigm is placed in central position of many investigations in the field of human machine interaction in these years. Precisited natural language addresses a model for dealing with vagueness of information and suggests a kind of knowledge representation, deduction and computational approach for natural language manipulation. Moreover, ontological architecture is an accepted model for developing this theory. In this work we are going to develop an ontology based question answering system which is one of crucial application of this paradigm.
{"title":"Towards a question answering system based on precisiated natural language","authors":"Mehdi Rohaninezhad, N. Omar","doi":"10.1109/STAIR.2011.5995771","DOIUrl":"https://doi.org/10.1109/STAIR.2011.5995771","url":null,"abstract":"Precisiated natural language is a new paradigm in soft computing based on information granulation. This paradigm is placed in central position of many investigations in the field of human machine interaction in these years. Precisited natural language addresses a model for dealing with vagueness of information and suggests a kind of knowledge representation, deduction and computational approach for natural language manipulation. Moreover, ontological architecture is an accepted model for developing this theory. In this work we are going to develop an ontology based question answering system which is one of crucial application of this paradigm.","PeriodicalId":376671,"journal":{"name":"2011 International Conference on Semantic Technology and Information Retrieval","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126379111","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2011-06-28DOI: 10.1109/STAIR.2011.5995803
R. Mohemad, A. Hamdan, Z. Othman, N. M. M. Noor
Tendering processes involves tedious and complex procedures. In construction, analysing a collection of tender documents is complicated and demanding task which requires in depth knowledge of domain experts. Inconsistency information and lack of knowledge during decision-making process could trigger to wrong decision. In addition, vast amount of information is in unstructured forms need to be managed into a systematic manner. The aim of this research is to develop a generic ontology-based architecture for supporting tendering processes and proves the effectiveness of the approach in construction tender evaluation process emphasizing only on checking sufficiency documents. Here, ontology is built to capture and structure domain expert knowledge based on criteria and preferences demand for tender evaluation.
{"title":"Modelling ontology for supporting construction tender evaluation process","authors":"R. Mohemad, A. Hamdan, Z. Othman, N. M. M. Noor","doi":"10.1109/STAIR.2011.5995803","DOIUrl":"https://doi.org/10.1109/STAIR.2011.5995803","url":null,"abstract":"Tendering processes involves tedious and complex procedures. In construction, analysing a collection of tender documents is complicated and demanding task which requires in depth knowledge of domain experts. Inconsistency information and lack of knowledge during decision-making process could trigger to wrong decision. In addition, vast amount of information is in unstructured forms need to be managed into a systematic manner. The aim of this research is to develop a generic ontology-based architecture for supporting tendering processes and proves the effectiveness of the approach in construction tender evaluation process emphasizing only on checking sufficiency documents. Here, ontology is built to capture and structure domain expert knowledge based on criteria and preferences demand for tender evaluation.","PeriodicalId":376671,"journal":{"name":"2011 International Conference on Semantic Technology and Information Retrieval","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124291247","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2011-06-28DOI: 10.1109/STAIR.2011.5995774
Amirah Ismail, M. Joy
Recent content management systems have restricted means for organizing and inferring documents although much of an organization's knowledge can be created in text repositories. In the Semantic Web search emergence, inferring and understanding can be deal by ontology-based semantic mark-up and metadata management. Whilst in the educational domain, learning objects are a fundamental resource. Literally, Content Management Systems and repositories have restricted the means for organising and understanding the captured semantic relationships between the learning objects and other stored documents. To cater this situation, we propose the application of metametadata as a useful semantic based approach to address similarities in a domain to gather definite requirements. This paper focuses on the existing approaches for describing semantic relationships in Content Management Systems and how metametadata capture the pedagogic information which can be applied to enhance the semantic information stored within such a Content Management Systems or repository. It is understood that there is still lacking approaches to address similarities in a domain that meets certain requirements but the progress for the ongoing research in the area is active and shows potential advancement.
{"title":"Semantic searches for extracting similarities in a content management system","authors":"Amirah Ismail, M. Joy","doi":"10.1109/STAIR.2011.5995774","DOIUrl":"https://doi.org/10.1109/STAIR.2011.5995774","url":null,"abstract":"Recent content management systems have restricted means for organizing and inferring documents although much of an organization's knowledge can be created in text repositories. In the Semantic Web search emergence, inferring and understanding can be deal by ontology-based semantic mark-up and metadata management. Whilst in the educational domain, learning objects are a fundamental resource. Literally, Content Management Systems and repositories have restricted the means for organising and understanding the captured semantic relationships between the learning objects and other stored documents. To cater this situation, we propose the application of metametadata as a useful semantic based approach to address similarities in a domain to gather definite requirements. This paper focuses on the existing approaches for describing semantic relationships in Content Management Systems and how metametadata capture the pedagogic information which can be applied to enhance the semantic information stored within such a Content Management Systems or repository. It is understood that there is still lacking approaches to address similarities in a domain that meets certain requirements but the progress for the ongoing research in the area is active and shows potential advancement.","PeriodicalId":376671,"journal":{"name":"2011 International Conference on Semantic Technology and Information Retrieval","volume":"72 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131008904","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2011-06-28DOI: 10.1109/STAIR.2011.5995796
Maytham Alabbas, A. Ramsay
The aim of the work reported here is to investigate the effectiveness of dependency parsing for the analysis of Arabic. Arabic has a number of characteristics, described below, which make parsing it particularly challenging. The results of our investigations suggest that dependency parsing can produce reasonably accurate results. We show in particular that combining the output of two different parsers can produce more accurate results than either parser produces by itself.
{"title":"Evaluation of dependency parsers for long Arabic sentences","authors":"Maytham Alabbas, A. Ramsay","doi":"10.1109/STAIR.2011.5995796","DOIUrl":"https://doi.org/10.1109/STAIR.2011.5995796","url":null,"abstract":"The aim of the work reported here is to investigate the effectiveness of dependency parsing for the analysis of Arabic. Arabic has a number of characteristics, described below, which make parsing it particularly challenging. The results of our investigations suggest that dependency parsing can produce reasonably accurate results. We show in particular that combining the output of two different parsers can produce more accurate results than either parser produces by itself.","PeriodicalId":376671,"journal":{"name":"2011 International Conference on Semantic Technology and Information Retrieval","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132693962","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2011-06-28DOI: 10.1109/STAIR.2011.5995773
Hazmy Iman Abas, M. Yusof, S. Noah
The paper discusses about the need for an ontological approach for a clinical decision support system (CDSS) in an acute postoperative pain management (APPM) setting. The paper describes the current issues in APPM, namely prescribing and technical errors due to clinicians' negligence of local guidelines, lack of continuous education and confusion on responsibilities and roles. The paper reviews about structured approaches to improve APPM which is to develop guidelines and algorithms, clinical paths, checklists, daily goals and improvements to health information systems. The approaches can be utilized by using an ontological approach to computerize the key concepts and relationships in APPM to allow terminology management, integration, interoperability and sharing of data, knowledge reuse and decision support. Few features that are important for CDSS are highlighted in this paper. A number of previous studies on the use of ontology to solve biomedical problems are also discussed. The paper also proposed the methodology for designing and developing an ontology-based CDSS for APPM.
{"title":"The application of ontology in a clinical decision support system for acute postoperative pain management","authors":"Hazmy Iman Abas, M. Yusof, S. Noah","doi":"10.1109/STAIR.2011.5995773","DOIUrl":"https://doi.org/10.1109/STAIR.2011.5995773","url":null,"abstract":"The paper discusses about the need for an ontological approach for a clinical decision support system (CDSS) in an acute postoperative pain management (APPM) setting. The paper describes the current issues in APPM, namely prescribing and technical errors due to clinicians' negligence of local guidelines, lack of continuous education and confusion on responsibilities and roles. The paper reviews about structured approaches to improve APPM which is to develop guidelines and algorithms, clinical paths, checklists, daily goals and improvements to health information systems. The approaches can be utilized by using an ontological approach to computerize the key concepts and relationships in APPM to allow terminology management, integration, interoperability and sharing of data, knowledge reuse and decision support. Few features that are important for CDSS are highlighted in this paper. A number of previous studies on the use of ontology to solve biomedical problems are also discussed. The paper also proposed the methodology for designing and developing an ontology-based CDSS for APPM.","PeriodicalId":376671,"journal":{"name":"2011 International Conference on Semantic Technology and Information Retrieval","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114923661","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2011-06-28DOI: 10.1109/STAIR.2011.5995805
Firdaus Banhawi, Nazlena Mohamad Ali
This paper describes our work in performing an exploratory factor analysis (EFA) to measure the engagement attributes in social network application (i.e. Facebook). We adapted the measuring user engagement scales from the previous work that have been done in an online shopping environment. By using factor analysis, we found that there are four attributes of engagement while interacting with social network application namely; Focus Attention, Novelty Endurabilty, Perceived Usability and Aesthetics. A number of 103 Facebook users responded to the administered questionnaires in two weeks duration. The findings show that respondents preferred using non-mobile devices as compared to both mobile and non-mobile devices in accessing and interacting with social network application.
{"title":"Measuring user engagement attributes in social networking application","authors":"Firdaus Banhawi, Nazlena Mohamad Ali","doi":"10.1109/STAIR.2011.5995805","DOIUrl":"https://doi.org/10.1109/STAIR.2011.5995805","url":null,"abstract":"This paper describes our work in performing an exploratory factor analysis (EFA) to measure the engagement attributes in social network application (i.e. Facebook). We adapted the measuring user engagement scales from the previous work that have been done in an online shopping environment. By using factor analysis, we found that there are four attributes of engagement while interacting with social network application namely; Focus Attention, Novelty Endurabilty, Perceived Usability and Aesthetics. A number of 103 Facebook users responded to the administered questionnaires in two weeks duration. The findings show that respondents preferred using non-mobile devices as compared to both mobile and non-mobile devices in accessing and interacting with social network application.","PeriodicalId":376671,"journal":{"name":"2011 International Conference on Semantic Technology and Information Retrieval","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132140541","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2011-06-28DOI: 10.1109/STAIR.2011.5995780
M. Mohd, F. Crestani, I. Ruthven
Interactive Topic Detection and Tracking (iTDT) is a branch of TDT research focusing on the aspects of user interface and user interaction. Thus, user tasks are the main focus in iTDT. This paper described the methodology used to design and to evaluate the Tracking and the Detection task. The tasks were designed to support the journalists to perform it in a way that it is in line with their task. Interactive Event Tracking System (iEvent) was used in the user experiment and the procedure of performing the TDT tasks using iEvent was explained.
{"title":"Evaluation task in Interactive Topic Detection and Tracking","authors":"M. Mohd, F. Crestani, I. Ruthven","doi":"10.1109/STAIR.2011.5995780","DOIUrl":"https://doi.org/10.1109/STAIR.2011.5995780","url":null,"abstract":"Interactive Topic Detection and Tracking (iTDT) is a branch of TDT research focusing on the aspects of user interface and user interaction. Thus, user tasks are the main focus in iTDT. This paper described the methodology used to design and to evaluate the Tracking and the Detection task. The tasks were designed to support the journalists to perform it in a way that it is in line with their task. Interactive Event Tracking System (iEvent) was used in the user experiment and the procedure of performing the TDT tasks using iEvent was explained.","PeriodicalId":376671,"journal":{"name":"2011 International Conference on Semantic Technology and Information Retrieval","volume":"34 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133969594","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：