{"title":"Exemplar-based complex features prediction framework","authors":"Mohamed Abou-Zleikha, Julie Carson-Berndsen","doi":"10.1109/NLPKE.2011.6138218","DOIUrl":"https://doi.org/10.1109/NLPKE.2011.6138218","url":null,"abstract":"Exemplars are typically defined by set of features that may have simple or complex structures. Comparing two exemplars requires a distance calculation between their features, a task which becomes more difficult when some of these features are missing. A possible solution is to predict the missing features making use of those that are known. Prediction of features is considered a hard task in machine learning and becomes more difficult when features have a complex structure and the relationship between the features is not clearly defined. This paper presents a framework for predicting complex features based on exemplar theory. The framework presented consists of two stages. The first stage is the similarity correlation stage, in which the correlation between the distance matrices of the features is calculated to determine the relationship between missing and existing features. The second stage calculates the conditional membership probability between these features using the distance matrices; this value determines the probability that for a new example not found in the dataset for which only some features are known, an exemplar with similar features to those of missing features that can be adapted to serve as appropriate features for the new example. This paper also presents a case study for the use of the framework in the context of speech synthesis. The framework is used to investigate the relationship between duration information and the syntactic and dependency trees.","PeriodicalId":362877,"journal":{"name":"2011 7th International Conference on Natural Language Processing and Knowledge Engineering","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115705842","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}
{"title":"Ambiguity spotting using wordnet semantic similarity in support to recommended practice for Software Requirements Specifications","authors":"Jin Matsuoka, Y. Lepage","doi":"10.1109/NLPKE.2011.6138247","DOIUrl":"https://doi.org/10.1109/NLPKE.2011.6138247","url":null,"abstract":"Word Sense Disambiguation is a crucial problem in documents whose purpose is to serve as specifications for automatic systems. The combination of different techniques of Natural Language Processing can help in this task. In this paper, we show how to detect ambiguous terms in Software Requirements Specifications. And we propose a computer-aided method that signals the reader for possibly ambiguous usage of terms. The method uses compound term measure (C-value), WordNet semantic similarity (WordNet wup_similarity) and a proposed semantic similarity measure between sentences.","PeriodicalId":362877,"journal":{"name":"2011 7th International Conference on Natural Language Processing and Knowledge Engineering","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125779575","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}
{"title":"A head-annotated synchronous context-free grammar for hierarchical phrase-based translation","authors":"Lemao Liu, T. Zhao, Chong Xu","doi":"10.1109/NLPKE.2011.6138168","DOIUrl":"https://doi.org/10.1109/NLPKE.2011.6138168","url":null,"abstract":"Hierarchical phrase-based translation is a state-of- the-art model. However, it does not consider the linguistic knowledge deeply as pure syntax-based model. In this paper, we propose a novel head-annotated synchronous context-free grammar for hierarchical phrase- based translation model. Our model contains several nonterminals in the synchronous rules. It can integrate some linguistic knowledge from head-modifier relationships of the words in source language. The experimental results obtain significant improvements in BLEU score over the NIST-05 task.","PeriodicalId":362877,"journal":{"name":"2011 7th International Conference on Natural Language Processing and Knowledge Engineering","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122737505","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}
Shoko Fuji, Mai Date, Yuko Nagai, Yuko Yasuhara, T. Tanioka, Fuji Ren
{"title":"Research on the possibility of humanoid robots to assist in medical activities in nursing homes and convalescent wards","authors":"Shoko Fuji, Mai Date, Yuko Nagai, Yuko Yasuhara, T. Tanioka, Fuji Ren","doi":"10.1109/NLPKE.2011.6138243","DOIUrl":"https://doi.org/10.1109/NLPKE.2011.6138243","url":null,"abstract":"In Japan, increasing attention has been given to using humanoid robots to solve problems concerning personnel shortage and to reduce duty workload in clinical and nursing situations. Currently, the development of robots is not yet at the level where they can function like human medical and health care professionals. For this reason, it is imperative to discover ways in which humanoid robots can be used to solve the issues of personnel shortage and duty workload. The aim of this research is to clarify the impressions nurse and care staff has toward humanoid robots. The research focuses on 1) whether there are any duties humanoids can undertake and 2) what is required of humanoids to perform clinical functions. This research was approved by the ethical review board of University Hospital A, and a mail survey was conducted between August and September, 2010. The respondents were 939 members of nurse and care staff working in nursing homes and convalescent wards. Among the reasons given by respondents who think that humanoids cannot do any clinical duty, the most common was “Not clear what and how much ability humanoids have,” chosen by 70.41 percent of respondents. Regarding the qualities required of humanoid robots on the aspect of ethical considerations, 63.79 percent chose “Not causing harm to humans,” making it the most common response. From the above results, it appears that personnel working in nursing homes and convalescent wards do not have enough accurate information on humanoid robots. It is therefore necessary that for future engagement of humanoid robots in clinical duty, advanced and detailed information on the ability and performance of humanoid robots be disseminated, so that not only patients but also medical staff can accept them without difficulty.","PeriodicalId":362877,"journal":{"name":"2011 7th International Conference on Natural Language Processing and Knowledge Engineering","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121595584","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}
{"title":"Manifesting Thai conceptual scenarios through Thai FrameNet","authors":"Dhanon Leenoi, Sawittree Jumpathong, T. Supnithi","doi":"10.1109/NLPKE.2011.6138183","DOIUrl":"https://doi.org/10.1109/NLPKE.2011.6138183","url":null,"abstract":"This paper presents the current status and caveat of the Thai FrameNet project. Through four modules, a combination approach: the expand and the merge, is implemented. The alignment of the original FrameNet is made by way of the former whilst the latter manifests the indigenous Thai conceptual scenarios. Currently, 1,339 frames, 22,708 lexical units, and 2,333 annotated sentences are obtained as a result. Frames are organised in the Thai FrameNet database and connected by seven frame-to-frame relations.","PeriodicalId":362877,"journal":{"name":"2011 7th International Conference on Natural Language Processing and Knowledge Engineering","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132200903","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}
{"title":"Procedural knowledge management system emergency management for nuclear power plants","authors":"H. Ikeda, Nestor Serrano-Cedillo, M. Ridwan","doi":"10.1109/NLPKE.2011.6138249","DOIUrl":"https://doi.org/10.1109/NLPKE.2011.6138249","url":null,"abstract":"This paper proposes state-oriented approach for knowledge management system, especially for risk management of nuclear power plants. The knowledge model is a kind of state flow in which each state is changed by actions and each action is activated by actors or states. To construct such knowledge base, huge manuals have been analyzed by a unique natural language processing algorithm, called a functional model of language. The authors used this knowledge model and developed an open-source platform for risk management. The system enables to develop procedural knowledge management systems that can check incompleteness, ambiguity and inconsistency of the set of procedures.","PeriodicalId":362877,"journal":{"name":"2011 7th International Conference on Natural Language Processing and Knowledge Engineering","volume":"231 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132291377","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}
M. Omori, Haruo Kobayashi, T. Tanioka, M. Nishimura, Atsuko Yuasa, Yuko Yasuhara
{"title":"An analysis of the stress of the elderly with dementia in day-care","authors":"M. Omori, Haruo Kobayashi, T. Tanioka, M. Nishimura, Atsuko Yuasa, Yuko Yasuhara","doi":"10.1109/NLPKE.2011.6138222","DOIUrl":"https://doi.org/10.1109/NLPKE.2011.6138222","url":null,"abstract":"The purpose of this study is to explain the stress levels of the elderly with dementia related to their daily behaviors observed using salivary amylase activity as a stress indicator. Study period was from September to October in 2005. Subjects were five people, and their cognitive abilities were assessed with Hasegawa's Dementia Scale-Revised (HDS-R). Their range of HDS-R scores were 0 to18. We obtained informed consent from subjects and their family. The experimental protocol used in this study was approved by the Ethics Committee at Kawasaki University. Salivary amylase activities were measured by the device of α-Amy Type 2.0 (Yamaha Co. LTD) and analyzed before and after occurrence daily activities. It was reported that salivary amylase activity correctly reacts to conditions of stress, via sympathetic-nervous-adrenomedullary system. We focused on their behavior or expressions and their reaction to others. Also it was analyzed the relations between their behavior and measured salivary amylase activities. In general, subjects' salivary amylase activities were increased, when they received rehabilitation, failed to communicate with the other elderly, their children and staff, estimated to participate the recreations and the busy bathing. On the other hand, their salivary amylase activities were decreased when they received music therapy, good communicated with other elderly, their children and staffs, and dozed off. In each case of the subjects, the changes of salivary amylase activity depended on how they can communicate with other people, whether or not they like to be alone, whether or not they are willing to participation to recreation activity. Their salivary amylase activities significantly were changed when they felt stress. Therefore, it was suggested that we must provide total care such as stress management for people with dementia","PeriodicalId":362877,"journal":{"name":"2011 7th International Conference on Natural Language Processing and Knowledge Engineering","volume":"300 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115929700","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}
{"title":"Extracting knowledge about cognitive style","authors":"G. Kellner, Bettina Berendt","doi":"10.1109/NLPKE.2011.6138172","DOIUrl":"https://doi.org/10.1109/NLPKE.2011.6138172","url":null,"abstract":"According to psycholinguistic research, any text contains a lot of implicit information about its writer. The Internet provides an incredible amount of text produced by users. The information potential of texts that can be directly linked to a user (which is especially the case for forum and blog posts) is not yet sufficiently examined. Natural language processing techniques are in some cases used for getting information on the user's personality, moods, affects and sentiments, but not yet for getting information on the user's cognitive style concerning sensory preference. This paper explores the potential of such an idea. Therefore, a corpus with more than 1.000.000 forum posts was analyzed for the occurrence of expressions that are directly linked to a sensory system. We found that users differ significantly in their use of sensory expressions and that most users have preferred patterns for the use of sensory expressions. Furthermore we found a correlation between the sensory vocabulary of a post and the sensory preference of the users who answered this post.","PeriodicalId":362877,"journal":{"name":"2011 7th International Conference on Natural Language Processing and Knowledge Engineering","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116397946","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}
{"title":"An advertising rhetorical mechanism for single event combined with conceptual dictionary in narrative generation system","authors":"Yike Zhang, Junpei Ono, Takashi Ogata","doi":"10.1109/NLPKE.2011.6138221","DOIUrl":"https://doi.org/10.1109/NLPKE.2011.6138221","url":null,"abstract":"This paper presents an advertising rhetorical analysis and an experimental system for scenario generation using the rhetoric. It is also an application of our narrative generation system combined with conceptual dictionary. The system has two aspects of micro generation, single event generation, and macro generation, the generation of scenario or story that is a sequence of events, and this paper mainly deals with a pilot system for the former. At the same time, we discuss ideas for the growth of single event generation and the expansion to scenario or story generation.","PeriodicalId":362877,"journal":{"name":"2011 7th International Conference on Natural Language Processing and Knowledge Engineering","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128501099","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}
{"title":"A comparison study of candidate generation for Chinese word segmentation","authors":"Kaixu Zhang, Maosong Sun","doi":"10.1109/NLPKE.2011.6138170","DOIUrl":"https://doi.org/10.1109/NLPKE.2011.6138170","url":null,"abstract":"Chinese word segmentation can be implemented in a coarse-to-fine schema. In such schema, a candidate set containing multiple segmentations of a sentence (rather than only one segmentation) is used as the output of a coarse-grained CWS model. Then a more sophisticated CWS model or other models of downstream tasks will reconsider all the segmentations in the candidate set to determine the best segmentation. This paper discussed and compared three candidate generation methods, namely boundary level method, word level method and sentence level method, in a unified form. The oracle F1-measures of the candidate sets of these methods were compared. The performances were also compared in a joint CWS and POS-tagging task. The results showed that the word level method has the best performance among these three candidate generation methods. Results also showed that the coarse-to-fine schema outperforms the pipeline schema in which only one segmentation is used for the downstream task and the joint schema in which all possible segmentation is used for the downstream task. Moreover, the speed of the coarse-to-fine schema is closed to the speed of the pipeline schema and much higher than the speed of the joint schema.","PeriodicalId":362877,"journal":{"name":"2011 7th International Conference on Natural Language Processing and Knowledge Engineering","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132410113","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}