Exploiting end of sentences and speaker alternations in language modeling for multiparty conversations

Hiroto Ashikawa, Naohiro Tawara, Atsunori Ogawa, Tomoharu Iwata, Tetsunori Kobayashi, Tetsuji Ogawa

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    1 Citation (Scopus)

    Abstract

    The effective handling of end-of-sentences and speaker alternations, both of which are frequently observed in multiparty conversations, in recurrent neural network language models (RNNLMs) is investigated. This kind of auxiliary information is represented as context cues and feature vectors. The former representation can be inserted directory into a transcription and treated as a word token, while the latter serves as auxiliary input to the neural networks. Experimental comparisons using multiparty conversation data, including the AMI meeting corpus, demonstrated that both representations contribute to improvement of the RNNLMs, and that dealing with the end-of-sentences is important, especially on the multiparty conversations.

    Original languageEnglish
    Title of host publicationProceedings - 9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017
    PublisherInstitute of Electrical and Electronics Engineers Inc.
    Pages1263-1267
    Number of pages5
    Volume2018-February
    ISBN (Electronic)9781538615423
    DOIs
    Publication statusPublished - 2018 Feb 5
    Event9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017 - Kuala Lumpur, Malaysia
    Duration: 2017 Dec 122017 Dec 15

    Other

    Other9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017
    CountryMalaysia
    CityKuala Lumpur
    Period17/12/1217/12/15

    Fingerprint

    Recurrent neural networks
    Transcription
    Neural networks

    ASJC Scopus subject areas

    • Artificial Intelligence
    • Human-Computer Interaction
    • Information Systems
    • Signal Processing

    Cite this

    Ashikawa, H., Tawara, N., Ogawa, A., Iwata, T., Kobayashi, T., & Ogawa, T. (2018). Exploiting end of sentences and speaker alternations in language modeling for multiparty conversations. In Proceedings - 9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017 (Vol. 2018-February, pp. 1263-1267). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/APSIPA.2017.8282217

    Exploiting end of sentences and speaker alternations in language modeling for multiparty conversations. / Ashikawa, Hiroto; Tawara, Naohiro; Ogawa, Atsunori; Iwata, Tomoharu; Kobayashi, Tetsunori; Ogawa, Tetsuji.

    Proceedings - 9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017. Vol. 2018-February Institute of Electrical and Electronics Engineers Inc., 2018. p. 1263-1267.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Ashikawa, H, Tawara, N, Ogawa, A, Iwata, T, Kobayashi, T & Ogawa, T 2018, Exploiting end of sentences and speaker alternations in language modeling for multiparty conversations. in Proceedings - 9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017. vol. 2018-February, Institute of Electrical and Electronics Engineers Inc., pp. 1263-1267, 9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017, Kuala Lumpur, Malaysia, 17/12/12. https://doi.org/10.1109/APSIPA.2017.8282217
    Ashikawa H, Tawara N, Ogawa A, Iwata T, Kobayashi T, Ogawa T. Exploiting end of sentences and speaker alternations in language modeling for multiparty conversations. In Proceedings - 9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017. Vol. 2018-February. Institute of Electrical and Electronics Engineers Inc. 2018. p. 1263-1267 https://doi.org/10.1109/APSIPA.2017.8282217
    Ashikawa, Hiroto ; Tawara, Naohiro ; Ogawa, Atsunori ; Iwata, Tomoharu ; Kobayashi, Tetsunori ; Ogawa, Tetsuji. / Exploiting end of sentences and speaker alternations in language modeling for multiparty conversations. Proceedings - 9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017. Vol. 2018-February Institute of Electrical and Electronics Engineers Inc., 2018. pp. 1263-1267
    @inproceedings{7383529d8bff437d849e09fc5ca8af0d,
    title = "Exploiting end of sentences and speaker alternations in language modeling for multiparty conversations",
    abstract = "The effective handling of end-of-sentences and speaker alternations, both of which are frequently observed in multiparty conversations, in recurrent neural network language models (RNNLMs) is investigated. This kind of auxiliary information is represented as context cues and feature vectors. The former representation can be inserted directory into a transcription and treated as a word token, while the latter serves as auxiliary input to the neural networks. Experimental comparisons using multiparty conversation data, including the AMI meeting corpus, demonstrated that both representations contribute to improvement of the RNNLMs, and that dealing with the end-of-sentences is important, especially on the multiparty conversations.",
    author = "Hiroto Ashikawa and Naohiro Tawara and Atsunori Ogawa and Tomoharu Iwata and Tetsunori Kobayashi and Tetsuji Ogawa",
    year = "2018",
    month = "2",
    day = "5",
    doi = "10.1109/APSIPA.2017.8282217",
    language = "English",
    volume = "2018-February",
    pages = "1263--1267",
    booktitle = "Proceedings - 9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017",
    publisher = "Institute of Electrical and Electronics Engineers Inc.",

    }

    TY - GEN

    T1 - Exploiting end of sentences and speaker alternations in language modeling for multiparty conversations

    AU - Ashikawa, Hiroto

    AU - Tawara, Naohiro

    AU - Ogawa, Atsunori

    AU - Iwata, Tomoharu

    AU - Kobayashi, Tetsunori

    AU - Ogawa, Tetsuji

    PY - 2018/2/5

    Y1 - 2018/2/5

    N2 - The effective handling of end-of-sentences and speaker alternations, both of which are frequently observed in multiparty conversations, in recurrent neural network language models (RNNLMs) is investigated. This kind of auxiliary information is represented as context cues and feature vectors. The former representation can be inserted directory into a transcription and treated as a word token, while the latter serves as auxiliary input to the neural networks. Experimental comparisons using multiparty conversation data, including the AMI meeting corpus, demonstrated that both representations contribute to improvement of the RNNLMs, and that dealing with the end-of-sentences is important, especially on the multiparty conversations.

    AB - The effective handling of end-of-sentences and speaker alternations, both of which are frequently observed in multiparty conversations, in recurrent neural network language models (RNNLMs) is investigated. This kind of auxiliary information is represented as context cues and feature vectors. The former representation can be inserted directory into a transcription and treated as a word token, while the latter serves as auxiliary input to the neural networks. Experimental comparisons using multiparty conversation data, including the AMI meeting corpus, demonstrated that both representations contribute to improvement of the RNNLMs, and that dealing with the end-of-sentences is important, especially on the multiparty conversations.

    UR - http://www.scopus.com/inward/record.url?scp=85050817222&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=85050817222&partnerID=8YFLogxK

    U2 - 10.1109/APSIPA.2017.8282217

    DO - 10.1109/APSIPA.2017.8282217

    M3 - Conference contribution

    AN - SCOPUS:85050817222

    VL - 2018-February

    SP - 1263

    EP - 1267

    BT - Proceedings - 9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017

    PB - Institute of Electrical and Electronics Engineers Inc.

    ER -