Effect of machine translation in interlingual conversation: Lessons from a formative study

• Main Authors: Kotaro HARA, IQBAL, Shamsi T.
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2015
• Subjects: Multilingual communication; Spoken language translation; Automatic speech recognition; Machine translation; Software Engineering
• Online Access: https://ink.library.smu.edu.sg/sis_research/4014; https://ink.library.smu.edu.sg/context/sis_research/article/5016/viewcontent/Hara_EffectOfMachineTranslationInInterlingualConversationLessonsFromAFormativeStudy_CHI2015.pdf
• Institution: Singapore Management University

Language barrier is the primary challenge for effectivecross-lingual conversations. Spoken language translation(SLT) is perceived as a cost-effective alternative to lessaffordable human interpreters, but little research has beendone on how people interact with such technology. Using aprototype translator application, we performed a formativeevaluation to elicit how people interact with the technologyand adapt their conversation style. We conducted two setsof studies with a total of 23 pairs (46 participants).Participants worked on storytelling tasks to simulate naturalconversations with 3 different interface settings. Ourfindings show that collocutors naturally adapt their style ofspeech production and comprehension to compensate forinadequacies in SLT. We conclude the paper with thedesign guidelines that emerged from the analysis.