TOP > Research > Comprehensive List of Researchers "Information Knowledge" > Department of Systems and Social Informatics > Architecture of Information Society Group > OHNO, Tomohiro

Comprehensive List of Researchers "Information Knowledge"

Department of Systems and Social Informatics

Name
OHNO, Tomohiro
Group
Architecture of Information Society Group
Title
Assistant Professor
Degree
Dr. of Information Science
Research Field
Natural language processing

Current Research

Natural Language Processing for Intellectual Activity Support

OUTLINE
We are researching natural language processing using a vast amount of linguistic information to support intellectual activities such as document creation and knowledge acquisition.

 

TOPICS

(1) Revision Support

Although Japanese has relatively free word order, Japanese word order is not completely arbitrary and has some sort of preference. Since such preference is incompletely understood, even native Japanese writers often write Japanese sentences which are grammatically well-formed but not easy to read. We are studying a new method for reordering words in a Japanese sentence so that the sentence becomes more readable for revision support. Although most of previous researches used syntactic information, the sentences they used there were what had been previously parsed. It is a problem that word reordering suffers the influence of parsing errors. Our proposed method concurrently performs dependency parsing and word reordering for an input sentence of which the dependency structure is still unknown. Our method can identify more suitable word order than conventional word reordering methods because it can concurrently consider the preference of both word order and dependency.

(2) Text-Style Conversion for Real-Time Captioning

Real-time captioning is a technique for supporting the speech understanding of deaf persons, elderly persons, or foreigners by displaying transcribed texts of monologue speech such as lectures. In monologues, since a sentence tends to be long, each sentence is often displayed in multi lines on one screen, it is necessary to insert linefeeds into a text so that the text becomes easy to read. We are developing a technique for inserting linefeeds into a Japanese spoken monologue text as an elemental technique to generate the readable captions. Our method can appropriately insert linefeeds into a sentence by machine learning, based on the information such as dependencies, clause boundaries, pauses and line length.

(3) Parsing for Spoken Language Application

In spoken language applications such as simultaneous machine interpretation and automatic real-time captioning, syntactic information is necessary to break away from keyword-based processing and achieve more advanced processing. We are developing a parsing method to deal with spoken language as base technology for the applications. We have so far developed the following parsers: (a) a robust parser for grammatically ill-formed linguistic phenomena in spoken language, (b) an efficient parser for extremely-long sentences in spoken monologue, (c) an incremental parser to execute processing simultaneously with speech input.

Career

  • 2007 July, Received Ph.D. degree in Information Science from Graduate School of Information Science, Nagoya University
  • 2007 August - 2007 August, Research Fellow of the Japan Society for the Promotion of Science (PD)
  • 2007 September - 2011 October, Assistant Professor at Graduate School of International Development, Nagoya University
  • 2011 November - Present, Assistant Professor at Information Technology Center, Nagoya University

Academic Societies

  • The Institute of Electronics, Information and Communication Engineering (IEICE)
  • Information Processing Society of Japan (IPSJ)
  • The Association for Natural Language Processing (ANLP)

Publications

  1. Japanese Word Reordering Integrated with Dependency Parsing, In Proceedings of the 25th International Conference on Computational Linguistics (COLING2014), pp. 1186-1196, 2014.
  2. Linefeed Insertion into Japanese Spoken Monologue for Captioning, In Proceedings of Joint Conference of the 47th Annual Meeting of the Association for Computational Linguistics and the 4th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing (ACL-IJCNLP2009), pp. 531-539, 2009.
  3. Incremental Dependency Parsing of Japanese Spoken Monologue Based on Clause Boundaries, The IEICE Transactions on Information and Systems (Japanese Edition),Vol. J90-D, No. 2, pp. 556-566, 2007.
  4. Dependency Parsing of Japanese Monologue Using Clause Boundaries, Language Resources and Evaluation, Vol. 40, No. 3/4, pp. 263-279, 2006.
  5. Robust Dependency Parsing of Spontaneous Japanese Spoken Language, The IEICE Transactions on Information and Systems, Vol. E88-D, No.3, pp. 545-552, 2005.