Keyword Search |
Researcher information
Yoichi Tomiura
Professor
Intelligence Science
Department of Informatics
Faculty of Information Science and Electrical Engineering
Last modified date:2024.04.29
Graduate SchoolProfessor
Intelligence Science
Department of Informatics
Faculty of Information Science and Electrical Engineering
Last modified date:2024.04.29
Undergraduate School
Other Organization
Homepage |
https://kyushu-u.elsevierpure.com/en/persons/yoichi-tomiura
Reseacher Profiling Tool Kyushu University Pure
Reseacher Profiling Tool Kyushu University Pure
Phone |
092-802-3584
Academic Degree |
Dr. Eng. (Kyushu University, Japan)
Country of degree conferring institution (Overseas) |
No
Field of Specialization |
Natural Language Processing
Total Priod of education and research career in the foreign country |
00years00months
Outline Activities |
He has been working in the field of Natural Language Processing. Especially, his research interests are : disambiguation of syntactic structure of a sentence, acquisition of the knowledge about words' meaning from a corpus, extraction of information from large set of documents, and comprehensive academic paper search.
Research |
Research Interests
- Extract spatial distribution of a target gas from mixed gas using the LSPR gas sensor
keyword : Multi-channel gas sensor, Matrix factorization, Component gas, Spatial distribution
2022.04. - Box Finder : Searching for Physical Documents in Archival Repositories
keyword : Historical documents, Box, Search
2023.04. - Research on odor quantification
keyword : Odor, Odor-code, embedding, SMILES, Olfactory Bulb
2021.03. - Research on semi-automated feedback on English learners' essays
keyword : Large Language Model, BERT, Unsupervised Learning
2023.02. - Research on research data retrieval
keyword : research data
2022.04. - A Comprehensive Study for Constructing a Large Scale Information Infrastructure of Paper-based Historical Materials
keyword : Historical Materials, OCR, Full-text Search, Information Infrastracture
2018.08~2022.03. - olfactory information processing using active pattern of glomeruli in the olfactory bulb
keyword : sense of smell, primitives of olfactory information, clustering of glomeruli
2014.10~2022.03. - Extracting Latent Research Cluster using Institute Repository
keyword : Author Topic Model, Topic Analysis, Collaboration, Research Administrator
2013.04~2016.03. - Automatically Generating Questions and Answers about Content of English Document Arbitrarily Selected by Learner Using NLP
keyword : generation of questions and answers, extensive reading, learning support, NLP
2012.04~2016.03. - Automatic Sentence-Level Annotation of Human Values
keyword : human values, opinion sentence, SVM, latent variable, Gibbs Sampling
2012.02~2021.03. - Organization of Scientific Papers for Scientific Information Retrieval
keyword : clustering, k-means, latent variable, statistic language model, distributional similarity, Gibbs Sampling
2011.04~2016.03. - Organization of Documents on WWW
keyword : Document Clustering, Estimation of Topic, Estimation of Relation between Clusters, Latent Class, Stochastic Language Model, BIC
2010.10~2012.03. - Analysis of Answering Method with Probability Conversion for Internet Research
keyword : Internet Research, anonymity, Probability Conversion
2007.07~2009.12. - Construction and publication of native/non-native English paper corpus gathered from Web and its application
keyword : Web document, discernment of nativeness, learner's corpus, English language education, supporting system for writing in English, NLP
2007.10~2012.03. - Providing Appropriate Alternative Co-occurrence Candidates; Towards a Japanese Composition Support System for Foreign Students
keyword : similarity of occurring environments, natural cooccurrence, Japanese composition support system, natural language processing
2008.06~2011.03. - Knowledge Acquisition about Meaning from Large Language Corpus
keyword : semantic category, case-frame, causal relation, self-organization, statistical language model, NLP
2003.08~2010.09. - Discernment of Nativeness of English Documents Based on Statistical Language Model
keyword : Web documents, Discernment of Nativeness, Statistical Language Model, Statistical Hypothesis Testing, NLP
2003.06~2009.09. - A Method for Automatically Generating Proper Responses to User's Utterances in Open-ended Conversation by Retrieving Documents on the Web
keyword : dialogue, open-domain, cohesion, coherence
2005.09~2009.08A knowledge-based dialog system makes the correct answer; however, it is unsuitable for open-ended input. On the other hand, Eliza makes open-ended conversation; however, it gives no new information to a user. We propose a new type of dialog system. Our dialog system lies between the two types of dialog systems xdescribed above, and makes conversation about various topics and gives information related to user's utterances. This type of dialog is useful for a new-idea generation for a user having an obscure desire to get information about his or her interest, but no concrete goal. Our system selects the proper sentence for the response to a user's utterance from a corpus. The most proper sentence is selected according to whether it satisfies surface cohesion and semantic coherence with the user's utterance. We made a trial system to make a conversation about movies and it showed that the proposed method is effective to search the proper response to user's open-ended utterances. . - Estimating Satisfactoriness of Selectional Restriction from Corpus
keyword : word cooccurrence, syntactic disambiguation, multiple regression model, natural language processing
1999.06~2004.03A selectional restriction specifies what combinations of words are semantically valid in a particular syntactic construction. This is one of the basic and important pieces of knowledge in Natural Language Processing, and has been used for syntactic disambiguation and word sense disambiguation. In the case of acquiring the selectional restriction for many combinations of words from a corpus, it is necessary to estimate whether or not a word combination that is not observed in the corpus satisfies the selectional restriction. This study proposed a new method for estimating the degree of satisfaction of the selectional restriction for a word combination from a tagged corpus, based on the multiple regression model. The independent variables of this model correspond to modifiers. Unlike a conventional multiple regression analysis, the independent variables are also parameters to be learned. We experiment on estimating the degree of satisfaction of the selectional restriction for Japanese word combinations. The experimental results indicate that our method estimates the degree of satisfaction of a word combination not observed in the corpus very well, and that the accuracy of syntactic disambiguation using the cooccurrencies estimated by our method is higher than using cooccurrence probabilities smoothed by previous methods. . - Placement of Nouns in a Multi-Dimensional Space Based on Words' Cooccurrency
keyword : word vector, cooccurrency, example-based method, natural language processing
2002.07~2003.10The semantic similarity (or distance) between words is one of the basic knowledge in Natural Language Processing. There have been several previous studies on measuring the similarity (or distance) based on word vectors in a multi-dimensional space. In those studies, high dimensional feature vectors of words are made from words' cooccurrence in a corpus or from reference relation in a dictionary, and then the word vectors are calculated from the feature vectors through the method like principal component analysis. This study proposed a new placement method of nouns into a multi-dimensional space based on words' cooccurrence in a corpus. The proposed method doesn't use the high dimensional feature vectors of words, but is based on the idea that ``vectors corresponding to nouns which cooccur with a word w in a relation f constitute a group in the multi-dimensional space''. Although the whole meaning of nouns isn't reflected in the word vectors obtained by the proposed method, the semantic similarity (or distance) between nouns defined with the word vectors is proper for an example-based disambiguation method. . - Robust Language Identification for Similar Languages and Short Texts
keyword : Language Identification, Similar Language, WWW, Information Retrieval
2004.08~2009.09A language identification is to estimate in what language a document is written, and is an important technology as a preprocess of information retrieval and natural language processing. This research proposes a language identification method which uses low-frequent byte-strings as language features. A general method identifies the language of a document by choosing the language which has the most similar probability distribution of byte-strings to that of the document. Most previous methods, whose similarity measures are based on frequencies of byte-strings, never use the low-frequent byte-strings because of the fluctuation of their frequencies. However, among low-frequent byte-strings, there are a lot of effective byte-strings in language identification, which tend to appear in a particular language. The similarity measure using not only frequent byte-strings but also low-frequent ones should be robust to the fluctuation of the probability and be sufficiently influenced by the low-frequent byte-strings. The similarity measure used in the proposed method is based on an intersection size of byte-strings between each language and a target document. Two kinds of preliminary examinations show that the proposed method has higher accuracy than the previous methods and has advantage in the language identification among similar languages or for short target documents. Now we are investigating revising the similarity measure and decreasing language features.. - Assisting with Translating Japanese Collocations Based on the Word Co-occurrence on the Web Texts
keyword : translation, Web document, cooccurrency, Word Sense Disambiguation
2003.08~2005.09A Method for Retrieving Translations of a Collocation in Web Data When a Japanese writer translates Japanese collocation(v^J is a Japanese verb, n^J is the object of v^J, and ``WO'' is the postpositional particle) into English collocation under the condition that he knows n^E to be the translation of n^J, there are some ways to get the proper translation of v^E as follows : (1) Looking up v^J in a Japanese-English dictionary and finding the proper translation of v^J referring examples, (2) Looking up some candidates for v^J in some English documents. The first way sometimes fails in getting the proper translation. And the second way needs a lot of time and manual efforts. If candidates of the proper v^E can be extracted from documents on WWW together with example sentences, it is easier to find the proper translation. This study proposes a new method for retrieving the proper English expression corresponding to a Japanese collocation using web data..
- Research on supporting the social science research through information science approach using a computer such as NLP
Papers
Presentations
Educational |
Educational Activities
[Graduate School of Information Science and Electrical Engineering]
Computational Linguistics
[Department of Library Science, Graduate School of Integrated Frontier Science]
Natural Language Analysis, Mathematical Statistics, Library Science Project Team Learning I, Advanced Study on Library Science I, Advanced Study on Library Science II
[Department of Electrical Engineering and Computer Science, School of Engineering]
Probability and Statistics (till 2007), Discrete Mathematics (since 2007), Laboratory of Electrical Engineering and Computer Science II (till 2007)
Computational Linguistics
[Department of Library Science, Graduate School of Integrated Frontier Science]
Natural Language Analysis, Mathematical Statistics, Library Science Project Team Learning I, Advanced Study on Library Science I, Advanced Study on Library Science II
[Department of Electrical Engineering and Computer Science, School of Engineering]
Probability and Statistics (till 2007), Discrete Mathematics (since 2007), Laboratory of Electrical Engineering and Computer Science II (till 2007)
Unauthorized reprint of the contents of this database is prohibited.
Copyright © 2006, Kyushu University. All rights reserved.