Search Results 1-20 of 3220

  • Joint dialog act segmentation and recognition in human conversations using attention to dialog context

    Zhao Tianyu , Kawahara Tatsuya

    … The proposed encoder–decoder outperforms other models in segmentation, and the application of attentions significantly reduces recognition error rates. …

    Computer Speech and Language (57), 108-127, 2019-09


  • Task-Based Language Education : Reflections on Implications and Criticisms

    Huber Arthur , Arthur Huber

    … This paper gives a brief account of the development of task-based language teaching (TBLT), from its initial aim as a critical response to both the "synthetic approach" and Presentation-Practice-Production (PPP), to its current usage in language learning contexts, as well as its own criticisms. … Several models of task-based frameworks are mentioned, including Skehan (1996), Willis (1996), Ellis (2003) and Nunan (2004). …

    Hirao School of Management review = Hirao School of Management review (9), 31-39, 2019-03-31

    IR DOI

  • Neural Language Models based on Conditional Hierarchical Recurrent Encoder-Decoder for Multi-Party Conversational Speech Recognition  [in Japanese]

    増村 亮 , 田中 智大 , 安藤 厚志 , 大庭 隆伸 , 青野 裕司

    電子情報通信学会技術研究報告 = IEICE technical report : 信学技報 118(495), 191-196, 2019-03-14

  • Neural Language Models based on Conditional Hierarchical Recurrent Encoder-Decoder for Multi-Party Conversational Speech Recognition  [in Japanese]

    増村 亮 , 田中 智大 , 安藤 厚志 , 大庭 隆伸 , 青野 裕司

    電子情報通信学会技術研究報告 = IEICE technical report : 信学技報 118(496), 191-196, 2019-03-14

  • 4.Educating the Educators of Tomorrow

    BERNING Brian , バーニング ブライアン

    … Today's students and tomorrow's teachersare facing challenges that without properpreparation and support will face strugglesat odds with what is required for teachingand learning English as a foreign language(EFL) in the Japanese context. … Our jobs aseducators at the University level requiresso much more than just the transmission ofthe English language. …

    英文オンライン=Eibun Online (1), 1-6, 2019-03


  • Viterbi Approximation of Latent Words Language Models for Automatic Speech Recognition

    Ryo Masumura , Taichi Asami , Takanobu Oba , Hirokazu Masataki , Sumitaka Sakauchi

    … This paper presents a Viterbi approximation of latent words language models (LWLMs) for automatic speech recognition (ASR). … Thisarticle should be cited as: Journal of Information Processing Vol.27(2019) (online)DOI paper presents a Viterbi approximation of latent words language models (LWLMs) for automatic speech recognition (ASR). …

    情報処理学会論文誌 60(2), 2019-02-15


  • Feature Based Domain Adaptation for Neural Network Language Models with Factorised Hidden Layers

    HENTSCHEL Michael , DELCROIX Marc , OGAWA Atsunori , IWATA Tomoharu , NAKATANI Tomohiro

    … <p>Language models are a key technology in various tasks, such as, speech recognition and machine translation. … They are usually used on texts covering various domains and as a result domain adaptation has been a long ongoing challenge in language model research. … With the rising popularity of neural network based language models, many methods have been proposed in recent years. …

    IEICE Transactions on Information and Systems E102.D(3), 598-608, 2019


  • The Role of the Medical Psychologists:―From My Experience at the Clinic―  [in Japanese]

    Matsuda Shiho

    <p>筆者は本学会認定の研修診療施設で指導を受け, その後個人メンタルクリニックで勤務をしている. 医療現場の心理士にとって必要な研修は何か, 重要な業務や役割について, 今までの経験から検討した. 現在のクリニックでは, 主に予診, 心理検査, 心理療法を業務として行う. 医師や他職種との情報共有は不可欠であり, 医学知識の習得は前提となる. 心理業務以外の柔軟な対応も期待されるが, …

    Japanese Journal of Psychosomatic Medicine 59(2), 125-129, 2019


  • Viterbi Approximation of Latent Words Language Models for Automatic Speech Recognition

    Masumura Ryo , Asami Taichi , Oba Takanobu , Masataki Hirokazu , Sakauchi Sumitaka

    … <p>This paper presents a Viterbi approximation of latent words language models (LWLMs) for automatic speech recognition (ASR). …

    Journal of Information Processing 27(0), 168-176, 2019


  • Automatic Generation of Train Timetables from Mesoscopic Railway Models by SMT-Solver

    ISOBE Yoshinao , HATSUGAI Hisabumi , TANAKA Akira , OIWA Yutaka , AMBE Takanori , OKADA Akimasa , KITAMURA Satoru , FUKUTA Yamato , KUNIFUJI Takashi

    … In this paper, we design a formal mesoscopic modeling language by analyzing real railways, for example <i>Tazawako-line</i> …

    IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences E102.A(2), 325-335, 2019


  • Preordering for Chinese-Vietnamese Statistical Machine Translation

    TRAN Huu-Anh , HUANG Heyan , TRAN Phuoc , SHI Shumin , NGUYEN Huu

    … However, Chinese-Vietnamese is a low-resource language pair, the extraction of reordering rules is limited. … The experimental results show that our methodology has improved the machine translation performance compared to the translation system using only the reordering models of phrase-based statistical machine translation.</p> …

    IEICE Transactions on Information and Systems E102.D(2), 375-382, 2019


  • The Basic Concepts and Reality of the Integration Course for Migrants and Refugees in Germany  [in Japanese]

    吉満 たか子

    … On this basis, the Commission has made various recommendations.The Commission considers that the German language is the key to integration and has examined the integration programs of other countries, especially the Netherlands and Sweden. … Based on the Dutch and Swedish models, the Commission came up with the basic concepts for the integration program in Germany.Most of the Commission's concepts and recommendations have been realized. …

    広島外国語教育研究 = Hiroshima studies in language and language education (22), 29-43, 2019

    IR DOI

  • Chord-aware automatic music transcription based on hierarchical Bayesian integration of acoustic and language models

    Ojima Yuta , Nakamura Eita , Itoyama Katsutoshi , Yoshii Kazuyoshi

    … Since chords and musical notes are deeply linked with each other, we propose joint pitch and chord estimation based on a Bayesian hierarchical model that consists of an acoustic model representing the generative process of a spectrogram and a language model representing the generative process of a piano roll. … The language model is formulated as a hidden Markov model that has chord labels as the latent variables and emits a piano roll. …

    APSIPA Transactions on Signal and Information Processing (7), 2018-11-22


  • The Prediction of Stock Market by Natural Language Processing and Deep Learning  [in Japanese]

    白方 健司 , 津田 博史 , シラカタ ケンジ , ツダ ヒロシ , Shirakata Kenji , Tsuda Hiroshi

    … 分回帰モデル)及び深層学習を用いた機械学習モデルにより株式市場の価格変動の予測を試みた.本研究の目的は,PCRモデルと比較することで,深層学習による機械学習モデルの有効性を検証することである.その際,機械学習モデルには,単純なリカレントニューラルネットワーク(RNN)を使用した.Recently, there are many motivations to quantify text data and use them for investment because the technology of the natural language processing has …

    同志社大学ハリス理化学研究報告 = The Harris science review of Doshisha University 59(3), 163-172, 2018-10

    IR DOI

  • Potential of Intrinsic Motivation Study for Japanese Learning in JFL Environment : On Learners Triggered by Japanese Popular Culture in Hong Kong  [in Japanese]

    小林 由子

    … Intrinsic Motivation is important for Japanese learners in JFL (Japanese as Foreign Language) environment because they often triggered by their interest in Japanese language or culture. … In many Japanese language education studies, motivation theory in SLA (Second Language Acquisition) studies are applied. … Motivation models in SLA study partly intake psychological theory but the psychological theory in SLA study does not renew. …

    国際広報メディア・観光学ジャーナル 27, 157-172, 2018-09-30


  • On the Construction of Translation in Partial Bidirectionalization

    Soichiro Hidaka , Massimo Tisi

    … In our previous work, we have proposed a general framework of partially translating UX languages to BX ones to fully maintain the expressive power of the UX languages while allowing backpropagable updates on a part of target models. … In an additive transformation language, sequences of language constructs at different level of well-defined syntactic hierarchy in a transformation can be shorten to produce smaller outputs. …

    情報処理学会論文誌プログラミング(PRO) 11(2), 26-26, 2018-06-26


  • CEFR-based Lexical Simplification Dataset

    Uchida Satoru , Takada Shohei , Arase Yuki

    … This study creates a language dataset for lexical simplification based on Common European Framework of References for Languages (CEFR) levels (CEFR-LS). … Lexical simplification has continued to be one of the important tasks for language learning and education.There are several language resources for lexical simplification that are available for generating rules and creating simplifiers using machine learning. …

    Proceedings of International Conference on Language Resources and Evaluation 11, 3254-3258, 2018-05


  • On the Development in the Models of Japanese Language Teaching at Chinese Universities  [in Japanese]

    郭 徳玉

    東京経済大学学術研究センター年報 = Annals of Tokyo Keizai University Academic Research Center (特別), 05-15, 2018-03-20


  • Mining Words in the Minds of Second Language Learners for Learner-specific Word Difficulty

    Yo Ehara , Issei Sato , Hidekazu Oiwa , Hiroshi Nakagawa

    … Therefore, we investigated theoretically and practically important models for predicting second language learners' vocabulary and propose another model for this vocabulary prediction task. … With the current models, the same word difficulty measure is shared by all learners. … Our model is also an extension of these current models in the sense that these models are special cases of our model. …

    情報処理学会論文誌 59(3), 2018-03-15


  • Practice of "essay writing" using various models  [in Japanese]

    山根 英明

    … There are many students who show hesitation and dissatisfaction when writing an essay was assigned in classes of Japanese language. …

    鳥取大学附属中学校研究紀要 49, 21-28, 2018-03-01


Page Top