Hideki Mima

Automatic recognition of multi-word terms:. the C-value/NC-value method

Abstract.Technical terms (henceforth called terms ), are important elements for digital libraries. In this paper we present a domain-independent method for the automatic extraction of multi-word terms, from machine-readable special language corpora. The method, (C-value/NC-value ), combines linguistic and statistical information. The first part, C-value, enhances the common statistical measure of frequency of occurrence for term extraction, making it sensitive to a particular type of multi-word terms, the nested terms. The second part, NC-value, gives: 1) a method for the extraction of term context words (words that tend to appear with terms); 2) the incorporation of information from term context words to the extraction of terms.

Terminology-driven literature mining and knowledge acquisition in biomedicine

In this paper we describe Tagged Information Management System (TIMS), an integrated knowledge management system for the domain of molecular biology and biomedicine, in which terminology-driven literature mining, knowledge acquisition (KA), knowledge integration (KI), and XML-based knowledge retrieval are combined using tag information management and ontology inference. The system integrates automatic terminology acquisition, term variation management, hierarchical term clustering, tag-based information extraction (IE), and ontology-based query expansion. TIMS supports introducing and combining different types of tags (linguistic and domain-specific, manual and automatic). Tag-based interval operations and a query language are introduced in order to facilitate KA and retrieval from XML documents. Through KA examples, we illustrate the way in which literature mining techniques can be utilised for knowledge discovery from documents.

Simultaneous Interpretation Utilizing Example-based Incremental Transfer

This paper describes a practical method of automatic simultaneous interpretation utilizing an example-based incremental transfer mechanism. We primarily show how incremental translation is achieved in the context of an example-based framework. We then examine the type of translation examples required for a simultaneous interpretation to create naturally communicative dialogs. Finally, we propose a scheme for automatic simultaneous interpretation exploiting this example-based incremental translation mechanism. Preliminary experimentation analyzing the performance of our example-based incremental translation mechanism leads us to believe that the proposed scheme can be utilized to achieve a practical simultaneous interpretation system.

The ATRACT Workbench: Automatic Term Recognition and Clustering for Terms

In this paper, we introduce a web-based integrated text and knowledge mining aid system in which information extraction and intelligent information retrieval/database access are combined using term-oriented natural language tools. Our work is placed within the BioPath research project whose overall aim is to link information extraction to expressed sequence data validation. The aim of the tool is to extract automatically terms, to cluster them, and to provide efficient access to heterogeneous biological and genomic databases and collections of texts, all wrapped into a user friendly workbench enabling users to use a wide range of textual and non textual resources effortlessly. For the evaluation, automatic term recognition and clustering techniques were applied in a domain of molecular biology. Besides English, the same workbench has been used for term recognition and clustering in Japanese.

A methodology for terminology-based knowledge acquisition and integration

In this paper we propose an integrated knowledge management system in which terminology-based knowledge acquisition, knowledge integration, and XML-based knowledge retrieval are combined using tag information and ontology management tools. The main objective of the system is to facilitate knowledge acquisition through query answering against XML-based documents in the domain of molecular biology. Our system integrates automatic term recognition, term variation management, context-based automatic term clustering, ontology-based inference, and intelligent tag information retrieval. Tag-based retrieval is implemented through interval operations, which prove to be a powerful means for textual mining and knowledge acquisition. The aim is to provide efficient access to heterogeneous biological textual data and databases, enabling users to integrate a wide range of textual and non-textual resources effortlessly.

Terminology-based knowledge mining for new knowledge discovery

In this article we present an integrated knowledge-mining system for the domain of biomedicine, in which automatic term recognition, term clustering, information retrieval, and visualization are combined. The primary objective of this system is to facilitate knowledge acquisition from documents and aid knowledge discovery through terminology-based similarity calculation and visualization of automatically structured knowledge. This system also supports the integration of different types of databases and simultaneous retrieval of different types of knowledge. In order to accelerate knowledge discovery, we also propose a visualization method for generating similarity-based knowledge maps. The method is based on real-time terminology-based knowledge clustering and categorization and allows users to observe real-time generated knowledge maps, graphically. Lastly, we discuss experiments using the GENIA corpus to assess the practicality and applicability of the system.

Integrating Multiple Dependency Corpora for Inducing Wide-Coverage Japanese CCG Resources

A novel method to induce wide-coverage Combinatory Categorial Grammar (CCG) resources for Japanese is proposed in this article. For some languages including English, the availability of large annotated corpora and the development of data-based induction of lexicalized grammar have enabled deep parsing, i.e., parsing based on lexicalized grammars. However, deep parsing for Japanese has not been widely studied. This is mainly because most Japanese syntactic resources are represented in chunk-based dependency structures, while previous methods for inducing grammars are dependent on tree corpora. To translate syntactic information presented in chunk-based dependencies to phrase structures as accurately as possible, integration of annotation from multiple dependency-based corpora is proposed. Our method first integrates dependency structures and predicate-argument information and converts them into phrase structure trees. The trees are then transformed into CCG derivations in a similar way to previously proposed methods. The quality of the conversion is empirically evaluated in terms of the coverage of the obtained CCG lexicon and the accuracy of the parsing with the grammar. While the transforming process used in this study is specialized for Japanese, the framework of our method would be applicable to other languages for which dependency-based analysis has been regarded as more appropriate than phrase structure-based analysis due to morphosyntactic features.

The Difference between the Two Representative Kampo Formulas for Treating Dysmenorrhea: An Observational Study

In Kampo medicine, two different formulas are effective for treating dysmenorrhea—tokishakuyakusan and keishibukuryogan; however, the criteria by which specialists select the appropriate formula for each patient are not clear. We compared patients treated with tokishakuyakusan and those with keishibukuryogan and proposed a predictive model. The study included 168 primary and secondary dysmenorrhea patients who visited the Kampo Clinic at Keio University Hospital. We collected clinical data from 128 dysmenorrhea patients, compared the two patient groups and selected significantly different factors as potential predictors, and used logistic regression to establish a model. An external validation was performed using 40 dysmenorrhea patients. Lightheadedness, BMI < 18.5, and a weak abdomen were significantly more frequent in the tokishakuyakusan group; tendency to sweat, heat intolerance, leg numbness, a cold sensation in the lower back, a strong abdomen, and paraumbilical tenderness and resistance were more frequent in the keishibukuryogan group. The final model fitted the data well. Internally estimated accuracy was 81.2%, and a leave-one-out cross-validation estimate of accuracy was 80.5%. External validation accuracy was 85.0%. We proposed a model for predicting the use of two Kampo formulas for dysmenorrhea, which should be validated in prospective trials.

XML tag information management system: a workbench for ontology-based knowledge acquisition and integration

In this paper, we propose an integrated information management system in which ontology-based knowledge integration and XML-based text/data retrieval are combined using tag information and ontology management tools. The main purpose of the system is to implement a query answering system for XML-based documents in the domain of molecular biology. The aim is to provide efficient access to heterogeneous biological and genomic textual data and databases, enabling users to use a wide range of textual and non-textual resources effortlessly. Our system includes automatic term recognition, context-based automatic term clustering, ontology-based inference, and intelligent tag information retrieval. Through further description of the implementation and architecture of the system, we will demonstrate how the system can accelerate knowledge integration on the textual and non-textual resources even for novice users of the field.

CAUSAL KNOWLEDGE EXTRACTION BY NATURAL LANGUAGE PROCESSING IN MATERIAL SCIENCE: A CASE STUDY IN CHEMICAL VAPOR DEPOSITION

Scientific publications written in natural language still play a central role as our knowledge source. However, due to the flood of publications, the literature survey process has become a highly time-consuming and tangled process, especially for novices of the discipline. Therefore, tools supporting the literature-survey process may help the individual scientist to explore new useful domains. Natural language processing (NLP) is expected as one of the promising techniques to retrieve, abstract, and extract knowledge. In this contribution, NLP is firstly applied to the literature of chemical vapor deposition (CVD), which is a sub-discipline of materials science and is a complex and interdisciplinary field of research involving chemists, physicists, engineers, and materials scientists. Causal knowledge extraction from the literature is demonstrated using NLP.