Quantitative Analysis for Simultaneous Interpreters using Large Scale Corpus

2017 Fiscal Year Final Research Report

• Project/Area Number: 25770146
• Research Category: Grant-in-Aid for Young Scientists (B)
• Allocation Type: Multi-year Fund
• Research Field: Linguistics
• Research Institution: Tsu City College (2015-2017); Nagoya University (2013-2014)
• Principal Investigator: RYU Koichiro 三重短期大学, その他部局等, 准教授 (40397451)
• Project Period (FY): 2013-04-01 – 2018-03-31
• Keywords: コーパス分析

Outline of Final Research Achievements

In one study, we have focused on the features of utterances that were spoken by simultaneous interpreters and we have classified the type of interpreters based on the features. In this classification, we have adopted a method that consisted of two phases, the principal component analysis (PCA) phase and the k-means clustering phase. In the result, we have acquired two principal components by PCA. Moreover, we have classified the interpreters into six types.
The other study is statistical analyses of missing translations in simultaneous interpretations. We analyzed the relationship between missing translations and various factors. The analyses revealed that the proportion of missing translations is high when the speech rate is high and delay is large. We also found that a high proportion of adverbs were missed in the translations, and that words at deeper positions in the syntactic structure were more likely to be missed.

Free Research Field

自然言語処理