Memory-based understanding of user utterances in a spoken dialogue system

Effects of feature selection and co-learning

A. van den Bosch

    Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

    92 Downloads (Pure)

    Abstract

    Understanding user utterances in human-computer spoken dialogue systems involves a multi-level pragmatic-semantic analysis of noisy natural language input streams. These analyses are heavily dependent on the dialogue context, and are complex due to the inherent ambiguity of language use, and to the errors induced by the intermediate speech recognition system. We review work on applying k-nearest-neighbour classification to this multi-level task split into (1) dialogue act classification, (2) slot filling identification, and (3) communication problem signalling, showing that co-learning some of these tasks produces superior results over learning them in isolation. We also show that additional feature selection can produce succinct feature sets, illustrating the viability of simple keyword-based shallow understanding.
    Original languageEnglish
    Title of host publicationWorkshop Proceedings of the 6th International Conference on Case-Based Reasoning, August 2005
    Place of PublicationChicago, IL
    Publisher[s.n.]
    Pages85-94
    Number of pages10
    Publication statusPublished - 2005

    Fingerprint

    Feature extraction
    Data storage equipment
    Speech recognition
    Semantics
    Communication

    Cite this

    van den Bosch, A. (2005). Memory-based understanding of user utterances in a spoken dialogue system: Effects of feature selection and co-learning. In Workshop Proceedings of the 6th International Conference on Case-Based Reasoning, August 2005 (pp. 85-94). Chicago, IL: [s.n.].
    van den Bosch, A. / Memory-based understanding of user utterances in a spoken dialogue system : Effects of feature selection and co-learning. Workshop Proceedings of the 6th International Conference on Case-Based Reasoning, August 2005. Chicago, IL : [s.n.], 2005. pp. 85-94
    @inproceedings{2c2cb8ac06ac4fb2bad9752135d9e444,
    title = "Memory-based understanding of user utterances in a spoken dialogue system: Effects of feature selection and co-learning",
    abstract = "Understanding user utterances in human-computer spoken dialogue systems involves a multi-level pragmatic-semantic analysis of noisy natural language input streams. These analyses are heavily dependent on the dialogue context, and are complex due to the inherent ambiguity of language use, and to the errors induced by the intermediate speech recognition system. We review work on applying k-nearest-neighbour classification to this multi-level task split into (1) dialogue act classification, (2) slot filling identification, and (3) communication problem signalling, showing that co-learning some of these tasks produces superior results over learning them in isolation. We also show that additional feature selection can produce succinct feature sets, illustrating the viability of simple keyword-based shallow understanding.",
    author = "{van den Bosch}, A.",
    note = "Pagination: 10",
    year = "2005",
    language = "English",
    pages = "85--94",
    booktitle = "Workshop Proceedings of the 6th International Conference on Case-Based Reasoning, August 2005",
    publisher = "[s.n.]",

    }

    van den Bosch, A 2005, Memory-based understanding of user utterances in a spoken dialogue system: Effects of feature selection and co-learning. in Workshop Proceedings of the 6th International Conference on Case-Based Reasoning, August 2005. [s.n.], Chicago, IL, pp. 85-94.

    Memory-based understanding of user utterances in a spoken dialogue system : Effects of feature selection and co-learning. / van den Bosch, A.

    Workshop Proceedings of the 6th International Conference on Case-Based Reasoning, August 2005. Chicago, IL : [s.n.], 2005. p. 85-94.

    Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

    TY - GEN

    T1 - Memory-based understanding of user utterances in a spoken dialogue system

    T2 - Effects of feature selection and co-learning

    AU - van den Bosch, A.

    N1 - Pagination: 10

    PY - 2005

    Y1 - 2005

    N2 - Understanding user utterances in human-computer spoken dialogue systems involves a multi-level pragmatic-semantic analysis of noisy natural language input streams. These analyses are heavily dependent on the dialogue context, and are complex due to the inherent ambiguity of language use, and to the errors induced by the intermediate speech recognition system. We review work on applying k-nearest-neighbour classification to this multi-level task split into (1) dialogue act classification, (2) slot filling identification, and (3) communication problem signalling, showing that co-learning some of these tasks produces superior results over learning them in isolation. We also show that additional feature selection can produce succinct feature sets, illustrating the viability of simple keyword-based shallow understanding.

    AB - Understanding user utterances in human-computer spoken dialogue systems involves a multi-level pragmatic-semantic analysis of noisy natural language input streams. These analyses are heavily dependent on the dialogue context, and are complex due to the inherent ambiguity of language use, and to the errors induced by the intermediate speech recognition system. We review work on applying k-nearest-neighbour classification to this multi-level task split into (1) dialogue act classification, (2) slot filling identification, and (3) communication problem signalling, showing that co-learning some of these tasks produces superior results over learning them in isolation. We also show that additional feature selection can produce succinct feature sets, illustrating the viability of simple keyword-based shallow understanding.

    M3 - Conference contribution

    SP - 85

    EP - 94

    BT - Workshop Proceedings of the 6th International Conference on Case-Based Reasoning, August 2005

    PB - [s.n.]

    CY - Chicago, IL

    ER -

    van den Bosch A. Memory-based understanding of user utterances in a spoken dialogue system: Effects of feature selection and co-learning. In Workshop Proceedings of the 6th International Conference on Case-Based Reasoning, August 2005. Chicago, IL: [s.n.]. 2005. p. 85-94