Neural-based automatic scoring model for Chinese-English interpretation with a multi-indicator assessment

Manual evaluation could be time-consuming, unreliable and unreproducible in Chinese-English interpretation. Therefore, it is necessary to develop an automatic scoring system. This paper proposes an accurate automatic scoring model for Chinese-English interpretation via a multi-indicator assessment....

Full description

Saved in:
Bibliographic Details
Main Authors: Xinguang Li, Xiaoning Li, Shuai Chen, Shanxian Ma, Fenfang Xie
Format: Article
Language:English
Published: Taylor & Francis Group 2022-12-01
Series:Connection Science
Subjects:
Online Access:http://dx.doi.org/10.1080/09540091.2022.2078279
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850169146929577984
author Xinguang Li
Xiaoning Li
Shuai Chen
Shanxian Ma
Fenfang Xie
author_facet Xinguang Li
Xiaoning Li
Shuai Chen
Shanxian Ma
Fenfang Xie
author_sort Xinguang Li
collection DOAJ
description Manual evaluation could be time-consuming, unreliable and unreproducible in Chinese-English interpretation. Therefore, it is necessary to develop an automatic scoring system. This paper proposes an accurate automatic scoring model for Chinese-English interpretation via a multi-indicator assessment. From the three dimensions (i.e. keywords, content, and grammar) of the scoring rubrics, three improved attention-based BiLSTM neural models are proposed to learn the text of the transcribed responses. In the feature vectorisation stage, the pre-training model Bert is utilised to vectorise the keywords and content, and a random initialisation is used for the grammar. In addition, the fluency is also taken into account based on the speech speed. The overall holistic score is obtained by fusing the four scores using the random forest regressor. The experimental results demonstrate that the proposed scoring method is effective and can perform as good as the manual scoring.
format Article
id doaj-art-a643012d2d3c46e8ba9439d08f8733fe
institution OA Journals
issn 0954-0091
1360-0494
language English
publishDate 2022-12-01
publisher Taylor & Francis Group
record_format Article
series Connection Science
spelling doaj-art-a643012d2d3c46e8ba9439d08f8733fe2025-08-20T02:20:48ZengTaylor & Francis GroupConnection Science0954-00911360-04942022-12-013411638165310.1080/09540091.2022.20782792078279Neural-based automatic scoring model for Chinese-English interpretation with a multi-indicator assessmentXinguang Li0Xiaoning Li1Shuai Chen2Shanxian Ma3Fenfang Xie4Guangdong University of Foreign StudiesGuangdong University of Foreign StudiesGuangdong University of Foreign StudiesGuangdong University of Foreign StudiesGuangdong University of Foreign StudiesManual evaluation could be time-consuming, unreliable and unreproducible in Chinese-English interpretation. Therefore, it is necessary to develop an automatic scoring system. This paper proposes an accurate automatic scoring model for Chinese-English interpretation via a multi-indicator assessment. From the three dimensions (i.e. keywords, content, and grammar) of the scoring rubrics, three improved attention-based BiLSTM neural models are proposed to learn the text of the transcribed responses. In the feature vectorisation stage, the pre-training model Bert is utilised to vectorise the keywords and content, and a random initialisation is used for the grammar. In addition, the fluency is also taken into account based on the speech speed. The overall holistic score is obtained by fusing the four scores using the random forest regressor. The experimental results demonstrate that the proposed scoring method is effective and can perform as good as the manual scoring.http://dx.doi.org/10.1080/09540091.2022.2078279automatic scoring modelchinese-english interpretationmulti-indicator assessmentattention mechanismbilstm
spellingShingle Xinguang Li
Xiaoning Li
Shuai Chen
Shanxian Ma
Fenfang Xie
Neural-based automatic scoring model for Chinese-English interpretation with a multi-indicator assessment
Connection Science
automatic scoring model
chinese-english interpretation
multi-indicator assessment
attention mechanism
bilstm
title Neural-based automatic scoring model for Chinese-English interpretation with a multi-indicator assessment
title_full Neural-based automatic scoring model for Chinese-English interpretation with a multi-indicator assessment
title_fullStr Neural-based automatic scoring model for Chinese-English interpretation with a multi-indicator assessment
title_full_unstemmed Neural-based automatic scoring model for Chinese-English interpretation with a multi-indicator assessment
title_short Neural-based automatic scoring model for Chinese-English interpretation with a multi-indicator assessment
title_sort neural based automatic scoring model for chinese english interpretation with a multi indicator assessment
topic automatic scoring model
chinese-english interpretation
multi-indicator assessment
attention mechanism
bilstm
url http://dx.doi.org/10.1080/09540091.2022.2078279
work_keys_str_mv AT xinguangli neuralbasedautomaticscoringmodelforchineseenglishinterpretationwithamultiindicatorassessment
AT xiaoningli neuralbasedautomaticscoringmodelforchineseenglishinterpretationwithamultiindicatorassessment
AT shuaichen neuralbasedautomaticscoringmodelforchineseenglishinterpretationwithamultiindicatorassessment
AT shanxianma neuralbasedautomaticscoringmodelforchineseenglishinterpretationwithamultiindicatorassessment
AT fenfangxie neuralbasedautomaticscoringmodelforchineseenglishinterpretationwithamultiindicatorassessment