• Search Research Projects
  • Search Researchers
  • How to Use
  1. Back to previous page

A study on compact and fast translation and language models for statistical machine translation

Research Project

Project/Area Number 15H02744
Research Category

Grant-in-Aid for Scientific Research (B)

Allocation TypeSingle-year Grants
Section一般
Research Field Intelligent informatics
Research InstitutionUniversity of Tsukuba

Principal Investigator

YAMAMOTO Mikio  筑波大学, システム情報系, 教授 (40210562)

Co-Investigator(Kenkyū-buntansha) 乾 孝司  筑波大学, システム情報系, 准教授 (60397031)
Research Collaborator NORIMATSU Jun-ya  
TANIGUCHI Masanori  
HAGA Shumpei  
OSUMI Kenji  
TAKENAKA Kousuke  
ISHII Akihiko  
Project Period (FY) 2015-04-01 – 2018-03-31
Project Status Completed (Fiscal Year 2017)
Budget Amount *help
¥16,120,000 (Direct Cost: ¥12,400,000、Indirect Cost: ¥3,720,000)
Fiscal Year 2017: ¥4,290,000 (Direct Cost: ¥3,300,000、Indirect Cost: ¥990,000)
Fiscal Year 2016: ¥5,070,000 (Direct Cost: ¥3,900,000、Indirect Cost: ¥1,170,000)
Fiscal Year 2015: ¥6,760,000 (Direct Cost: ¥5,200,000、Indirect Cost: ¥1,560,000)
Keywords言語モデル / ダブル配列 / 部分転置ダブル配列 / ランダム配置 / 統計的機械翻訳 / トライ / ngram言語モデル / ngramモデル / シングル配列
Outline of Final Research Achievements

Although DALM (Double-Array Language Model) is a fast and compact implementation of ngram language models, it fails to fully capitalize on quantization techniques for values of model parameters such as probabilities of ngrams, because of a structual limitation: it stores values and indexes in the common array. In this study, we developed some variants of DALM which have separate arrays for values and indexes and can exploit benefits of quantization. We investigated basic characteristics of DALM empirically and propose "partly transposed double-array" which is a key technique to educe the ability of DALMs with separate arrays.

Report

(4 results)
  • 2017 Annual Research Report   Final Research Report ( PDF )
  • 2016 Annual Research Report
  • 2015 Annual Research Report
  • Research Products

    (5 results)

All 2018 2017 2016

All Journal Article (2 results) (of which Peer Reviewed: 2 results,  Acknowledgement Compliant: 2 results) Presentation (3 results)

  • [Journal Article] A fast and compact language model implementation using double-array structures2016

    • Author(s)
      Jun-Ya Norimatsu, Makoto Yasuhara, Toru Tanaka and Mikio Yamamoto
    • Journal Title

      ACM Transactions on Asian and Low-Resource Language Information Processing

      Volume: 15(4)

    • Related Report
      2016 Annual Research Report
    • Peer Reviewed / Acknowledgement Compliant
  • [Journal Article] A fast and compact language model implementation using double-array structures2016

    • Author(s)
      Jun-ya Norimatsu, Makoto Yasuhara, Toru Tanaka and Mikio Yamamoto
    • Journal Title

      ACM Transaction of Asian Low-resource language information processing

      Volume: 印刷中

    • Related Report
      2015 Annual Research Report
    • Peer Reviewed / Acknowledgement Compliant
  • [Presentation] 細粒度並列処理によるダブル配列言語モデルの構築高速化2018

    • Author(s)
      石井瑛彦、芳賀駿平、竹中孝介、大隈賢二、山本幹雄
    • Organizer
      第24回言語処理学会年次大会
    • Related Report
      2017 Annual Research Report
  • [Presentation] 部分転置ダブル配列を用いたngram言語モデルの実装2017

    • Author(s)
      竹中孝介, 芳賀駿平, 山本幹雄
    • Organizer
      言語処理学会第23回年次大会
    • Place of Presentation
      筑波大学(茨城県つくば市)
    • Year and Date
      2017-03-13
    • Related Report
      2016 Annual Research Report
  • [Presentation] 部分転置ダブルアレイを用いたngram言語モデルの検討2016

    • Author(s)
      芳賀俊平, 谷口正訓, 山本幹雄
    • Organizer
      第30回人工知能学会全国大会
    • Place of Presentation
      北九州国際会議場(福岡県北九州市)
    • Year and Date
      2016-06-06
    • Related Report
      2016 Annual Research Report

URL: 

Published: 2015-04-16   Modified: 2019-03-29  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi