Zobrazeno 1 - 10 of 66 pro vyhledávání: '"Hiroshi Fujimura"'
1
Transfer Learning for Unseen Slots in End-to-End Dialogue State Tracking
Autor: Hiroshi Fujimura, Masami Akamine, Iwata Kenji, Yoshida Takami
Publikováno v: Lecture Notes in Electrical Engineering ISBN: 9789811593222
IWSDS
This paper proposes a transfer learning algorithm for end-to-end dialogue state tracking (DST) to handle new slots with a small set of training data, which has not yet been discussed in the literature on conventional approaches. The goal of transfer
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::11e2f5d481db2b0f73f5ff590e3c882b
https://doi.org/10.1007/978-981-15-9323-9_5
Zobrazit plný text záznamu
3
Dialog State Tracking with Incorporation of Target Values in Attention Models
Autor: Hiroshi Fujimura, Iwata Kenji, Kobayashi Yuka, Yoshida Takami
Publikováno v: Lecture Notes in Electrical Engineering ISBN: 9789811583940
IWSDS
This paper proposes a fully data-driven approach to dialog state tracking (DST) that can handle new slot values not seen during training. The approach is based on a long short-term memory recurrent neural network with an attention mechanism. Unlike w
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::bdb4fc47f9ba8edca051508e667c65e5
https://doi.org/10.1007/978-981-15-8395-7_9
Zobrazit plný text záznamu
7
Dialog State Tracking for Unseen Values Using an Extended Attention Mechanism
Autor: Yoshida Takami, Masami Akamine, Hiroshi Fujimura, Iwata Kenji
Publikováno v: Lecture Notes in Electrical Engineering ISBN: 9789811394423
Recently, discriminative models using recurrent neural networks (RNNs) have shown good performance for dialog state tracking (DST). However, the models have difficulty in handling new dialog states unseen in model training. This paper proposes a full
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::a1b123e8b0d0f10c3f6296050ba4ce56
https://doi.org/10.1007/978-981-13-9443-0_7
Zobrazit plný text záznamu
8
Out-of-Domain Slot Value Detection for Spoken Dialogue Systems with Context Information
Autor: Masami Akamine, Kobayashi Yuka, Yoshida Takami, Hiroshi Fujimura, Iwata Kenji
Publikováno v: SLT
This paper proposes an approach to detecting-of-domain slot values from user utterances in spoken dialogue systems based on contexts. The approach detects keywords of slot values from utterances and consults domain knowledge (i.e., an ontology) to ch
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::a9212f9e81a9a7894cd93c67d1c860e1
https://doi.org/10.1109/slt.2018.8639671
Zobrazit plný text záznamu
9
Applying Complex-Valued Neural Networks to Acoustic Modeling for Speech Recognition
Autor: Takashi Masuko, Hiroshi Fujimura, Daichi Hayakawa
Publikováno v: APSIPA
Complex-valued neural networks (CVNNs) are well suited to speech signal processing because they can naturally represent amplitude and phase. In this paper, we explore applying an acoustic model with multiple complex-valued layers (multiple-CVNN-AM) a
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::181c98970c263deeaa58db602d9edb0f
https://doi.org/10.23919/apsipa.2018.8659610
Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání

Omezení vyhledávání
Plný text Recenzováno Digitální knihovna AV ČR
Zdroje