Learning culturally situated dialogue strategies to support language learners

Victoria Abou-Khalil, Toru Ishida, Masayuki Otani, Brendan Flanagan, Hiroaki Ogata, Donghui Lin

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Successful language learning requires an understanding of the target culture in order to make valuable usage of the learned language. To understand a foreign culture, language students need the knowledge of its related products, as well as the skill of comparing them to those of their own culture. One way for students to understand foreign products is by making Culturally Situated Associations (CSA), i.e., relating the products they encountered to products from their own culture. In order to provide students with CSA that they can understand, we must gather information about their culture, provide them with the CSA, and make sure they understand it. In this case, a Culturally Situated Dialogue (CSD) must take place. To carry the dialogue, dialogue systems must follow a dialogue strategy. However, previous work showed that handcrafted dialogue strategies were shown to be ineffective in comparison with machine-learned dialogue strategies. In this research, we proposed a method to learn CSD strategies to support foreign students, using a reinforcement learning algorithm. Since no previous system providing CSA was implemented, the method allowed the creation of CSD strategies when no initial data or prototype exists. The method was applied to generate three different agents: the novice agent was based on an eight states feature-space, the intermediate agent was based on a 144 states feature-space, and the advanced agent was based on a 288 states feature-space. Each of these agents learned a different dialogue strategy. We conducted a Wizard of Oz experiment during which, the agents’ role was to support the wizard in their dialogue with students by providing them with the appropriate action to take at each step. The resulting dialogue strategies were evaluated based on the quality of the strategy. The results suggest the use of the novice agent at the first stages of prototyping the dialogue system. The intermediate agent and the advanced agent could be used at later stages of the system’s implementation.

Original languageEnglish
Article number10
JournalResearch and Practice in Technology Enhanced Learning
Volume13
Issue number1
DOIs
Publication statusPublished - 2018 Dec 1
Externally publishedYes

Fingerprint

Language
dialogue
Learning
Students
language
learning
communication technology
student
Situated learning
foreign student
Reinforcement learning
Learning algorithms
Research
reinforcement
experiment
Experiments

Keywords

  • Automatic dialogue strategies
  • Culturally situated information
  • Intercultural competence
  • Language learning
  • Reinforcement learning
  • Wizard of Oz

ASJC Scopus subject areas

  • Education
  • Social Psychology
  • Media Technology
  • Management of Technology and Innovation

Cite this

Learning culturally situated dialogue strategies to support language learners. / Abou-Khalil, Victoria; Ishida, Toru; Otani, Masayuki; Flanagan, Brendan; Ogata, Hiroaki; Lin, Donghui.

In: Research and Practice in Technology Enhanced Learning, Vol. 13, No. 1, 10, 01.12.2018.

Research output: Contribution to journalArticle

Abou-Khalil, Victoria ; Ishida, Toru ; Otani, Masayuki ; Flanagan, Brendan ; Ogata, Hiroaki ; Lin, Donghui. / Learning culturally situated dialogue strategies to support language learners. In: Research and Practice in Technology Enhanced Learning. 2018 ; Vol. 13, No. 1.
@article{61a3ce06e1cc4889ae3efe1ec8660edd,
title = "Learning culturally situated dialogue strategies to support language learners",
abstract = "Successful language learning requires an understanding of the target culture in order to make valuable usage of the learned language. To understand a foreign culture, language students need the knowledge of its related products, as well as the skill of comparing them to those of their own culture. One way for students to understand foreign products is by making Culturally Situated Associations (CSA), i.e., relating the products they encountered to products from their own culture. In order to provide students with CSA that they can understand, we must gather information about their culture, provide them with the CSA, and make sure they understand it. In this case, a Culturally Situated Dialogue (CSD) must take place. To carry the dialogue, dialogue systems must follow a dialogue strategy. However, previous work showed that handcrafted dialogue strategies were shown to be ineffective in comparison with machine-learned dialogue strategies. In this research, we proposed a method to learn CSD strategies to support foreign students, using a reinforcement learning algorithm. Since no previous system providing CSA was implemented, the method allowed the creation of CSD strategies when no initial data or prototype exists. The method was applied to generate three different agents: the novice agent was based on an eight states feature-space, the intermediate agent was based on a 144 states feature-space, and the advanced agent was based on a 288 states feature-space. Each of these agents learned a different dialogue strategy. We conducted a Wizard of Oz experiment during which, the agents’ role was to support the wizard in their dialogue with students by providing them with the appropriate action to take at each step. The resulting dialogue strategies were evaluated based on the quality of the strategy. The results suggest the use of the novice agent at the first stages of prototyping the dialogue system. The intermediate agent and the advanced agent could be used at later stages of the system’s implementation.",
keywords = "Automatic dialogue strategies, Culturally situated information, Intercultural competence, Language learning, Reinforcement learning, Wizard of Oz",
author = "Victoria Abou-Khalil and Toru Ishida and Masayuki Otani and Brendan Flanagan and Hiroaki Ogata and Donghui Lin",
year = "2018",
month = "12",
day = "1",
doi = "10.1186/s41039-018-0076-x",
language = "English",
volume = "13",
journal = "Research and Practice in Technology Enhanced Learning",
issn = "1793-7078",
publisher = "Springer Open",
number = "1",

}

TY - JOUR

T1 - Learning culturally situated dialogue strategies to support language learners

AU - Abou-Khalil, Victoria

AU - Ishida, Toru

AU - Otani, Masayuki

AU - Flanagan, Brendan

AU - Ogata, Hiroaki

AU - Lin, Donghui

PY - 2018/12/1

Y1 - 2018/12/1

N2 - Successful language learning requires an understanding of the target culture in order to make valuable usage of the learned language. To understand a foreign culture, language students need the knowledge of its related products, as well as the skill of comparing them to those of their own culture. One way for students to understand foreign products is by making Culturally Situated Associations (CSA), i.e., relating the products they encountered to products from their own culture. In order to provide students with CSA that they can understand, we must gather information about their culture, provide them with the CSA, and make sure they understand it. In this case, a Culturally Situated Dialogue (CSD) must take place. To carry the dialogue, dialogue systems must follow a dialogue strategy. However, previous work showed that handcrafted dialogue strategies were shown to be ineffective in comparison with machine-learned dialogue strategies. In this research, we proposed a method to learn CSD strategies to support foreign students, using a reinforcement learning algorithm. Since no previous system providing CSA was implemented, the method allowed the creation of CSD strategies when no initial data or prototype exists. The method was applied to generate three different agents: the novice agent was based on an eight states feature-space, the intermediate agent was based on a 144 states feature-space, and the advanced agent was based on a 288 states feature-space. Each of these agents learned a different dialogue strategy. We conducted a Wizard of Oz experiment during which, the agents’ role was to support the wizard in their dialogue with students by providing them with the appropriate action to take at each step. The resulting dialogue strategies were evaluated based on the quality of the strategy. The results suggest the use of the novice agent at the first stages of prototyping the dialogue system. The intermediate agent and the advanced agent could be used at later stages of the system’s implementation.

AB - Successful language learning requires an understanding of the target culture in order to make valuable usage of the learned language. To understand a foreign culture, language students need the knowledge of its related products, as well as the skill of comparing them to those of their own culture. One way for students to understand foreign products is by making Culturally Situated Associations (CSA), i.e., relating the products they encountered to products from their own culture. In order to provide students with CSA that they can understand, we must gather information about their culture, provide them with the CSA, and make sure they understand it. In this case, a Culturally Situated Dialogue (CSD) must take place. To carry the dialogue, dialogue systems must follow a dialogue strategy. However, previous work showed that handcrafted dialogue strategies were shown to be ineffective in comparison with machine-learned dialogue strategies. In this research, we proposed a method to learn CSD strategies to support foreign students, using a reinforcement learning algorithm. Since no previous system providing CSA was implemented, the method allowed the creation of CSD strategies when no initial data or prototype exists. The method was applied to generate three different agents: the novice agent was based on an eight states feature-space, the intermediate agent was based on a 144 states feature-space, and the advanced agent was based on a 288 states feature-space. Each of these agents learned a different dialogue strategy. We conducted a Wizard of Oz experiment during which, the agents’ role was to support the wizard in their dialogue with students by providing them with the appropriate action to take at each step. The resulting dialogue strategies were evaluated based on the quality of the strategy. The results suggest the use of the novice agent at the first stages of prototyping the dialogue system. The intermediate agent and the advanced agent could be used at later stages of the system’s implementation.

KW - Automatic dialogue strategies

KW - Culturally situated information

KW - Intercultural competence

KW - Language learning

KW - Reinforcement learning

KW - Wizard of Oz

UR - http://www.scopus.com/inward/record.url?scp=85062679768&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85062679768&partnerID=8YFLogxK

U2 - 10.1186/s41039-018-0076-x

DO - 10.1186/s41039-018-0076-x

M3 - Article

VL - 13

JO - Research and Practice in Technology Enhanced Learning

JF - Research and Practice in Technology Enhanced Learning

SN - 1793-7078

IS - 1

M1 - 10

ER -