2026-09-19T14:01:00Zhttps://dspace.mit.edu/server/oai/requestoai:dspace.mit.edu:1721.1/756522022-01-13T07:54:29Zcom_1721.1_7582com_1721.1_7581col_1721.1_131022
Stephanie Seneff.
Xu, Yushi, Ph. D. Massachusetts Institute of Technology
Massachusetts Institute of Technology. Dept. of Electrical Engineering and Computer Science.
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
2012-12-13T18:49:25Z
2012-12-13T18:49:25Z
2012
2012
http://hdl.handle.net/1721.1/75652
818354293
Thesis (Ph. D.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2012.
Cataloged from PDF version of thesis.
Includes bibliographical references (p. 237-244).
Second language learning has become an important societal need over the past decades. Given that the number of language teachers is far below demand, computer-aided language learning software is becoming a promising supplement to traditional classroom learning, as well as potentially enabling new opportunities for self-learning. The use of speech technologies is especially attractive to offer students unlimited chances for speaking exercises. To create helpful and intelligent speaking exercises on a computer, it is necessary for the computer to not only recognize the acoustics, but also to understand the meaning and give appropriate responses. Nevertheless, most existing speech-enabled language learning software focuses only on speech recognition and pronunciation training. Very few have emphasized exercising the student's composition and comprehension abilities and adopting language technologies to enable free-form conversation emulating a real human tutor. This thesis investigates the critical functionalities of a computer-aided language learning system, and presents a generic framework as well as various language- and domain-independent modules to enable building complex speech-based language learning systems. Four games have been designed and implemented using the framework and the modules to demonstrate their usability and flexibility, where dynamic content creation, automatic assessment, and automatic assistance are emphasized. The four games, reading, translation, question-answering and dialogue, offer different activities with gradually increasing difficulty, and involve a wide range of language processing techniques, such as language understanding, language generation, question generation, context resolution, dialogue management and user simulation. User studies with real subjects show that the systems were well received and judged to be helpful.
by Yushi Xu.
Ph.D.
244 p.
eng
Massachusetts Institute of Technology
M.I.T. theses are protected by
copyright. They may be viewed from this source for any purpose, but
reproduction or distribution in any format is prohibited without written
permission. See provided URL for inquiries about permission.
http://dspace.mit.edu/handle/1721.1/7582
Electrical Engineering and Computer Science.
Language technologies in speech-enabled second language learning games : from reading to dialogue
Thesis
application/pdf
false
Publication
unknown
unknown
<Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="b758a629-0d4a-4ce1-b6ed-5c370f484e1c">
<Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type>
<Language>eng</Language>
<Title>Language technologies in speech-enabled second language learning games : from reading to dialogue</Title>
<PublishedIn>
<Publication>
</Publication>
</PublishedIn>
<PublicationDate>2012</PublicationDate>
<Authors>
<Author>
<DisplayName>Xu, Yushi, Ph. D. Massachusetts Institute of Technology</DisplayName>
<Affiliation>
<OrgUnit>
</OrgUnit>
</Affiliation>
</Author>
</Authors>
<Editors>
</Editors>
<Publishers>
<Publisher>
<DisplayName>Massachusetts Institute of Technology</DisplayName>
<OrgUnit />
</Publisher>
</Publishers>
<License>http://dspace.mit.edu/handle/1721.1/7582</License>
<Keyword>Electrical Engineering and Computer Science.</Keyword>
<Abstract>Second language learning has become an important societal need over the past decades. Given that the number of language teachers is far below demand, computer-aided language learning software is becoming a promising supplement to traditional classroom learning, as well as potentially enabling new opportunities for self-learning. The use of speech technologies is especially attractive to offer students unlimited chances for speaking exercises. To create helpful and intelligent speaking exercises on a computer, it is necessary for the computer to not only recognize the acoustics, but also to understand the meaning and give appropriate responses. Nevertheless, most existing speech-enabled language learning software focuses only on speech recognition and pronunciation training. Very few have emphasized exercising the student's composition and comprehension abilities and adopting language technologies to enable free-form conversation emulating a real human tutor. This thesis investigates the critical functionalities of a computer-aided language learning system, and presents a generic framework as well as various language- and domain-independent modules to enable building complex speech-based language learning systems. Four games have been designed and implemented using the framework and the modules to demonstrate their usability and flexibility, where dynamic content creation, automatic assessment, and automatic assistance are emphasized. The four games, reading, translation, question-answering and dialogue, offer different activities with gradually increasing difficulty, and involve a wide range of language processing techniques, such as language understanding, language generation, question generation, context resolution, dialogue management and user simulation. User studies with real subjects show that the systems were well received and judged to be helpful.</Abstract>
<Access xmlns="http://purl.org/coar/access_right"
>
</Access>
</Publication>