Powered by OpenAIRE graph
Found an issue? Give us feedback
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ ZENODOarrow_drop_down
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
ZENODO
Article . 2019
License: CC BY
Data sources: Datacite
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
ZENODO
Article . 2019
License: CC BY
Data sources: Datacite
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
ZENODO
Article . 2019
License: CC BY
Data sources: ZENODO
versions View all 2 versions
addClaim

Chatbots for Multilingual Conversations

Authors: Mahesh Vanjani; Milam Aiken; Mina Park;

Chatbots for Multilingual Conversations

Abstract

Chatbots emulate human dialogue to provide a more intuitive user interface to applications or simply provide entertainment. Chatbots rely on technology to function and new and emerging technologies such as NLP (Natural Language Processing) and AI (Artificial Intelligence) can be used to increase the ability of chatbots to emulate a more natural and free flowing conversation. As more and more mobile device users transition to increased use of texts and messaging chatbots can be used to provide consumers with multilingual support and services. While some chatbots have been developed in other languages, currently most converse only in English, and only a few can communicate in multiple languages. If configured correctly multilingual chatbots have the potential of providing a digital communication option that transcends language barriers. For our research we focused on the use of a chatbot that links the English-speaking Tutor Mike system with Google Translate, thus providing conversational capability in 103 languages, which is more than any other artificial multilingual agent is currently capable of. Two humans communicated with the system using German, Spanish, and Korean, and a group of undergraduate students reviewed the English translations of the chatbot’s replies. Results show that the responses from German and Spanish were cogent and natural, but those from Korean were less understandable. As a caveat, Asian languages lack much of the linguistic nuances of European languages. For example, there may be no plural form or gender in the Asian language. Unlike German where nouns and adjectives constantly change endings depending on what they are doing in a sentence and, unlike Spanish, which have numerous verb conjugations, Asian languages require no such changes. This might impact the translation ability and quality of a multilingual chatbot. Additional research and enhancements can improve chatbots used for European to Asian language translations and vice-versa. Regardless, our research shows promising results in the future use of multilingual chatbots to allow communication across the globe with business potential in the use of such chatbots to provide customer service and online live interaction with customers across the world.

Keywords

Chatbot, Multilingual, Communication, Machine Translation

  • BIP!
    Impact byBIP!
    selected citations
    These citations are derived from selected sources.
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    5
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Top 10%
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
    OpenAIRE UsageCounts
    Usage byUsageCounts
    visibility views 24
    download downloads 17
  • 24
    views
    17
    downloads
    Powered byOpenAIRE UsageCounts
Powered by OpenAIRE graph
Found an issue? Give us feedback
visibility
download
selected citations
These citations are derived from selected sources.
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
views
OpenAIRE UsageCountsViews provided by UsageCounts
downloads
OpenAIRE UsageCountsDownloads provided by UsageCounts
5
Top 10%
Average
Average
24
17
Green