Proper Name Machine Translation from Japanese to Japanese Sign Language

نویسندگان

  • Taro Miyazaki
  • Naoto Kato
  • Seiki Inoue
  • Shuichi Umeda
  • Makiko Azuma
  • Nobuyuki Hiruma
  • Yuji Nagashima
چکیده

This paper describes machine translation of proper names from Japanese to Japanese Sign Language (JSL). “Proper name transliteration” is a kind of machine translation of proper names between spoken languages and involves character-tocharacter conversion based on pronunciation. However, transliteration methods cannot be applied to Japanese-JSL machine translation because proper names in JSL are composed of words rather than characters. Our method involves not only pronunciation-based translation, but also sense-based translation, because kanji, which are ideograms that compose most Japanese proper names, are closely related to JSL words. These translation methods are trained from parallel corpora. The sense-based translation part is trained via phrase alignment in sentence pairs in a Japanese and JSL corpus. The pronunciation-based translation part is trained from a Japanese proper name corpus and then post-processed with transformation rules. We conducted a series of evaluation experiments and obtained 75.3% of accuracy rate, increasing from baseline method by 19.7 points. We also developed a Japanese-JSL proper name translation system, in which the translated proper names are visualized with CG animations.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Indonesian-Japanese CLIR Using Only Limited Resource

Our research aim here is to build a CLIR system that works for a language pair with poor resources where the source language (e.g. Indonesian) has limited language resources. Our IndonesianJapanese CLIR system employs the existing Japanese IR system, and we focus our research on the IndonesianJapanese query translation. There are two problems in our limited resource query translation: the OOV p...

متن کامل

Coling • Acl 2006

Our research aim here is to build a CLIR system that works for a language pair with poor resources where the source language (e.g. Indonesian) has limited language resources. Our IndonesianJapanese CLIR system employs the existing Japanese IR system, and we focus our research on the IndonesianJapanese query translation. There are two problems in our limited resource query translation: the OOV p...

متن کامل

On the Web Communication Assist Aide based on the Bilingual Sign Language Dictionary

We discuss the basic ideas behind a Japanese to American Sign Language Translation System for the Japanese users, which assists Japanese Deaf people to communicate. Our discussion covers two main points. The first describes the necessity of a Sign Language Translation System. Since there is no “universal sign language” or real “international sign language,” if Deaf people should learn at least ...

متن کامل

A Method of Cross Language Question-Answering Based on Machine Translation and Transliteration - Yokohama National University at NTCIR-5 CLQA1

We propose methods of English-Japanese and Japanese-English cross language question-answering (E-J/J-E CLQA) that use machine translation (MT), transliteration, and an existing Japanese QA system that deeply depends on Japanese. With regard to the E-J task, in order to compensate the insufficiencies in the bilingual dictionary of an MT system, we utilize the documents on the Web to translate pr...

متن کامل

Generation of modifier representation in sign animation

Most of the Japanese-to-JSL (Japanese Sign Language) translators utilize CG (Computer Graphics) animation to present translation results. However, foregoing systems cannot produce natural and legible sign expressions for the Deaf, because they are based on word-for-word translation. Our research aims to produce animation including proper modifier representation, which can express nuances of ori...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2014