Context-sensitive and role-dependent spoken language understanding using bidirectional and attention LSTMs

Chiori Hori, Takaaki Hori, Shinji Watanabe, John R. Hershey

Research output: Contribution to journalArticle

9 Citations (Scopus)

Abstract

To understand speaker intentions accurately in a dialog, it is important to consider the context of the surrounding sequence of dialog turns. Furthermore, each speaker may play a different role in the conversation, such as agent versus client, and thus features related to these roles may be important to the context. In previous work, we proposed context-sensitive spoken language understanding (SLU) using role-dependent long short-term memory (LSTM) recurrent neural networks (RNNs), and showed improved performance at predicting concept tags representing the intentions of agent and client in a human-human hotel reservation task. In the present study, we use bidirectional and attention-based LSTMs to train a roledependent context-sensitive model to jointly represent both the local word-level context within each utterance, and the left and right context within the dialog. The different roles of client and agent are modeled by switching between role-dependent layers. We evaluated label accuracies in the hotel reservation task using a variety of models, including logistic regression, RNNs, LSTMs, and the proposed bidirectional and attentionbased LSTMs. The bidirectional and attention-based LSTMs yield significantly better performance in this task.

Original languageEnglish
Pages (from-to)3236-3240
Number of pages5
JournalUnknown Journal
Volume08-12-September-2016
DOIs
Publication statusPublished - 2016
Externally publishedYes

Fingerprint

Hotels
Recurrent neural networks
Dependent
Context sensitive languages
Reservation
Recurrent Neural Networks
Logistics
Labels
conversation
Memory Term
Logistic Regression Model
logistics
Context
Language
Spoken Language Understanding
regression analysis
Dialogue
Long short-term memory
Human
Model

Keywords

  • Attention LSTMs
  • Bidirectional LSTMs
  • Context sensitive understanding
  • Role-dependent model
  • Spoken language understanding

ASJC Scopus subject areas

  • Language and Linguistics
  • Human-Computer Interaction
  • Signal Processing
  • Software
  • Modelling and Simulation

Cite this

Context-sensitive and role-dependent spoken language understanding using bidirectional and attention LSTMs. / Hori, Chiori; Hori, Takaaki; Watanabe, Shinji; Hershey, John R.

In: Unknown Journal, Vol. 08-12-September-2016, 2016, p. 3236-3240.

Research output: Contribution to journalArticle

Hori, Chiori ; Hori, Takaaki ; Watanabe, Shinji ; Hershey, John R. / Context-sensitive and role-dependent spoken language understanding using bidirectional and attention LSTMs. In: Unknown Journal. 2016 ; Vol. 08-12-September-2016. pp. 3236-3240.
@article{4f6391e930124ff6ae8c463a1e71124d,
title = "Context-sensitive and role-dependent spoken language understanding using bidirectional and attention LSTMs",
abstract = "To understand speaker intentions accurately in a dialog, it is important to consider the context of the surrounding sequence of dialog turns. Furthermore, each speaker may play a different role in the conversation, such as agent versus client, and thus features related to these roles may be important to the context. In previous work, we proposed context-sensitive spoken language understanding (SLU) using role-dependent long short-term memory (LSTM) recurrent neural networks (RNNs), and showed improved performance at predicting concept tags representing the intentions of agent and client in a human-human hotel reservation task. In the present study, we use bidirectional and attention-based LSTMs to train a roledependent context-sensitive model to jointly represent both the local word-level context within each utterance, and the left and right context within the dialog. The different roles of client and agent are modeled by switching between role-dependent layers. We evaluated label accuracies in the hotel reservation task using a variety of models, including logistic regression, RNNs, LSTMs, and the proposed bidirectional and attentionbased LSTMs. The bidirectional and attention-based LSTMs yield significantly better performance in this task.",
keywords = "Attention LSTMs, Bidirectional LSTMs, Context sensitive understanding, Role-dependent model, Spoken language understanding",
author = "Chiori Hori and Takaaki Hori and Shinji Watanabe and Hershey, {John R.}",
year = "2016",
doi = "10.21437/Interspeech.2016-1171",
language = "English",
volume = "08-12-September-2016",
pages = "3236--3240",
journal = "Nuclear Physics A",
issn = "0375-9474",
publisher = "Elsevier",

}

TY - JOUR

T1 - Context-sensitive and role-dependent spoken language understanding using bidirectional and attention LSTMs

AU - Hori, Chiori

AU - Hori, Takaaki

AU - Watanabe, Shinji

AU - Hershey, John R.

PY - 2016

Y1 - 2016

N2 - To understand speaker intentions accurately in a dialog, it is important to consider the context of the surrounding sequence of dialog turns. Furthermore, each speaker may play a different role in the conversation, such as agent versus client, and thus features related to these roles may be important to the context. In previous work, we proposed context-sensitive spoken language understanding (SLU) using role-dependent long short-term memory (LSTM) recurrent neural networks (RNNs), and showed improved performance at predicting concept tags representing the intentions of agent and client in a human-human hotel reservation task. In the present study, we use bidirectional and attention-based LSTMs to train a roledependent context-sensitive model to jointly represent both the local word-level context within each utterance, and the left and right context within the dialog. The different roles of client and agent are modeled by switching between role-dependent layers. We evaluated label accuracies in the hotel reservation task using a variety of models, including logistic regression, RNNs, LSTMs, and the proposed bidirectional and attentionbased LSTMs. The bidirectional and attention-based LSTMs yield significantly better performance in this task.

AB - To understand speaker intentions accurately in a dialog, it is important to consider the context of the surrounding sequence of dialog turns. Furthermore, each speaker may play a different role in the conversation, such as agent versus client, and thus features related to these roles may be important to the context. In previous work, we proposed context-sensitive spoken language understanding (SLU) using role-dependent long short-term memory (LSTM) recurrent neural networks (RNNs), and showed improved performance at predicting concept tags representing the intentions of agent and client in a human-human hotel reservation task. In the present study, we use bidirectional and attention-based LSTMs to train a roledependent context-sensitive model to jointly represent both the local word-level context within each utterance, and the left and right context within the dialog. The different roles of client and agent are modeled by switching between role-dependent layers. We evaluated label accuracies in the hotel reservation task using a variety of models, including logistic regression, RNNs, LSTMs, and the proposed bidirectional and attentionbased LSTMs. The bidirectional and attention-based LSTMs yield significantly better performance in this task.

KW - Attention LSTMs

KW - Bidirectional LSTMs

KW - Context sensitive understanding

KW - Role-dependent model

KW - Spoken language understanding

UR - http://www.scopus.com/inward/record.url?scp=84994235660&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84994235660&partnerID=8YFLogxK

U2 - 10.21437/Interspeech.2016-1171

DO - 10.21437/Interspeech.2016-1171

M3 - Article

VL - 08-12-September-2016

SP - 3236

EP - 3240

JO - Nuclear Physics A

JF - Nuclear Physics A

SN - 0375-9474

ER -