Available via license: CC BY-NC 4.0
Content may be subject to copyright.
Application of Computer-Aided Translation
in Interpretation Learning Under the New
Liberal Arts Horizon
Renna Gui(B)
School of Foreign Languages, Nanchang Institute of Technology, Nanchang, China
86050651@qq.com
Abstract. In the context of the development and prosperity of economic global-
ization, translation, as a means of information transmission in intercultural com-
munication, plays an increasingly important role. The translation market has an
increasing demand for talents, which requires higher quality of talents. However,
the training speed of translation talents in colleges and universities is relatively
slow. This paper mainly studies the application of computer-aided translation in
interpreting learning from the perspective of new liberal arts. This paper first intro-
duces the new arts and computer-aided translation related content, and then dis-
cusses the application of computer-aided translation in practical teaching. Through
the comparison of the results of pre-test and post-test, it can be seen that the experi-
mental class which applied computer-aided translation in interpreting learning has
made great progress, showing a difference with the control class.
Keywords: New Liberal Arts Perspective ·Computer-Aided Translation ·
Interpretation Learning ·Interdisciplinary
1 Introduction
Its application has penetrated into various fields including the education industry, which
has had a huge impact on the traditional work, study and life style, and the traditional
teaching method has also undergone a huge change. Education informationization is
the requirement of the times, the computer-aided instruction system for subject courses
has changed the traditional teaching mode and met the requirements of the develop-
ment of current education informationization. “Internet +Education” has transformed
the traditional education model, and education has adapted to the requirements of The
Times. Nowadays, with the development of economic globalization and the prosperity
of international cultural exchanges, translation has played a decisive role. In the future,
the translation market will have higher requirements on the quality of translation talents
and the demand will be greater. It is imperative to accelerate the cultivation of translation
talents and improve their quality. Computer-aided translation originates from computer-
aided language learning, that is, using multimedia assisted interpretation training [1].
The opportunities provided by computer-aided translation are very stimulating and chal-
lenging for interpreting teachers and trainees. In addition to the training received in the
© The Author(s) 2023
Z. Zhan et al. (Eds.): EIMSS 2022, AHCS 7, pp. 633–640, 2023.
https://doi.org/10.2991/978-94-6463-024-4_66
634 R. Gui
classroom, it is also important for students to receive additional training, feedback and
materials after class [2].
Computer Assisted Instruction, or CAI, uses a Computer system to help teachers
teach students. The United States is the first country to study and apply the computer-
assisted instruction system. Most of the foreign research and development in this field,
following the main line of development of the United States, has experienced 60 years
from the beginning of the application, and now the development is booming, the appli-
cation is more and more extensive, the system is more and more mature [3]. At present,
many colleges and universities have introduced computer-aided Translation teaching
system into foreign language Translation teaching. Computer-aided Translation (CAT)
commonly used include SDL Trados, Memoq, Omegaat, Snowman CAT, Langri CAT,
etc. [4]. In addition, there are server versions of CAT software, such as Chuanshen, Yaxin
and other foreign language training platforms or machine-assisted translation teaching
systems. Compared with the advanced experience of foreign countries, although China
has begun to recognize the role of computer-aided translation, its importance is still
poorly understood [5].
Based on the computer aided translation of network technology, translation memory
technology and database technology, this paper provides an information-based indepen-
dent teaching platform for teachers and students. To improve the level of translation and
translation innovation ability, improve the quality of translation personnel, to meet the
needs of translation personnel in today’s era.
2 Computer-Aided Interpretation Learning in the New Liberal
Arts Vision
2.1 The Main Content and Significance of New Arts
The New arts compared with the traditional arts, is the global new revolution of sci-
ence and technology, economic development and socialism with Chinese characteristics
into a new era as the background, to break the liberal arts, inheritance and innovation,
cross and fusion of traditional mode of thinking, to share together as main way, pro-
moting multidisciplinary cross, depth fusion, promote upgrading traditional art, from
the subject orientation to demand oriented, From professional segmentation to cross
integration, from service adaptation to support guidance.” In this definition, it highlights
the most distinctive feature of the new liberal arts that is different from the traditional
liberal arts – interdisciplinary [6]. New arts stressed discipline between open and inclu-
sive, comprehensive and connectivity, should break the barriers between disciplines and
the traditional disciplines, cross and penetration, enhance dialogue, in the process of
interdisciplinarity explore the new growing point of the traditional disciplines, promote
innovative research, to create a new academic frontiers.
The concept of the new liberal arts has important epochal significance. The new arts
emerge as The Times demand, which is reflected in the following aspects: Is a mod-
ern industrial show highly complex, large scale development pattern, the key point of
modern science and technology, major theoretical breakthrough and innovative tech-
nological inventions appear more in the infiltration of communion between disciplines,
Application of Computer-Aided Translation in Interpretation Learning 635
more questions depend on the different experts in the field of cooperation, resources inte-
gration, the whole chain of innovation. This requires that the new liberal arts must play
an important role in the new round of scientific and technological revolution and indus-
trial reform, train comprehensive talents and provide necessary think tank support in the
development of emerging technologies such as artificial intelligence, genetic engineer-
ing, virtual technology and block chain. Secondly, the traditional liberal arts cannot fully
meet the new requirements of the new era to some extent, which also urgently requires
the liberal arts to adjust and improve themselves in the new era [7]. For example, in
terms of research scope, the use and promotion of big data analysis technology, human-
computer interaction, machine learning, knowledge mapping and the social attributes
of artificial intelligence are in urgent need of more participation and cooperation of lib-
eral arts talents. In terms of research methods, traditional research topics of liberal arts,
such as consciousness, language and psychological mechanism, also use and transplant
interdisciplinary research methods for in-depth exploration.
2.2 Computer-Aided Translation Technology
Since the birth of computer in 1947, the academic circles began to try to use computer for
machine aided translation (CAT). The development process of CAT translation method
reflects the different stages of people using computer to realize automatic translation.
The first stage is based on the method of language rules, which holds that as long as the
theory and means of human translation are “instilled” into the computer, it can simulate
human to realize translation, but language rules cannot cover complex and changeable
language phenomena. The second stage is the empirical method of learning from the
actual language. Both obtaining translation templates from translation examples or statis-
tical model Translation (SMT) belong to this category. The third stage is neural network
translation (NMT), which is an end-to-end overall translation model. The progress of
these three research methods reflects the transformation roadmap of machine translation
strategy: from imitating human translation rules to the analysis and reorganization of
language structural components, and then to the translation strategy of integration [8].
Google found that in the translation of multiple samples, the neural network machine
translation system reduced the error by 55%–85% or more. However, the training cost
of NMT is still too high. Google brain researchers Denny britz, Anna Goldie, thang
Luong and Quoc Le conducted a large-scale analysis on the super parameters of NMT
architecture, and put forward some novel ideas and practical suggestions for establishing
and expanding NMT architecture.
This section mainly introduces terminology management techniques, translation
memorization technology and corpus management system. Terminology management
techniques and tools include Excel, Access, SDL Multi Term, Word Fast, etc. The general
functions of a term management tool are to extract terms, create, manage and maintain a
term database, edit term data, retrieve and filter terms, share and publish terms, set data
security, etc. Due to the continuous updating and development of technology, the term
management system has realized the standardization, networking and integration [9].
Translation memory technique is one of the computer aided translation techniques. Its
working principle is as follows: Translated version will have been fed into a computer,
to save the original in the translation memory, when open the translation software,
636 R. Gui
translation memory software translator will each fragment and memories in the data
analysis of the existing translation remained contrast, can be extracted in the translation
of the original memory in the library search the same or similar libraries, translation
results provide reference for the translator, the translator can choose, edit or abandoned.
The new translation does not need to be repeated, but only needs to refer to and use the
previous translation results, so as to avoid unnecessary duplication of work by users,
thus greatly improving the translation efficiency.
Corpus management of computer-aided translation software can be divided into word
base management and sentence base management. This paper mainly analyzes vocabu-
lary management. A term is a term for a particular subject. A glossary is a list of bilingual
or multilingual comparison words, including auxiliary information such as definition,
subject, part of speech, etc. [10]. There are cloud corpus data platforms at home and
abroad. The famous one abroad is TAUS Data Cloud. TAUS is the abbreviation of Trans-
lation Automation User Society. Headquartered in Amsterdam, the Netherlands, TAUS
is a platform to provide data sharing and translation cutting-edge knowledge for the
global language and translation industry. It aims to provide strategic suggestions for the
language service industry and help formulate industry standards. Domestic corpus data
platforms mainly include Tmxmall and UTH. Among them, Tmxmall provides corpus
online alignment, focusing on the research and application of cloud corpus big data prod-
ucts and technologies, real-time monitoring system integration technology, private cloud
corpus management and corpus mall trading platform. Translators can complete corpus
production and corpus management and utilization by using its online alignment and pri-
vate cloud. The interactive interface of the corpus alignment tool “online alignment” is
humanized, and the accuracy of alignment results is high. Its intelligent alignment algo-
rithm can automatically align the sentences of “one to many, many to one, many to many”
in the original and translated corpus, greatly reducing the manual workload. Up to now,
the platform has accumulated hundreds of millions of pairs of high-quality corpus, cov-
ering news, politics, law, finance, machinery, medicine, patents, construction and other
vertical fields. UTH is mainly engaged in corpus big data infrastructure construction and
language application technology innovation. Its parallel corpus involves 33 languages,
covering cross-border e-commerce, international engineering, equipment manufactur-
ing, film and television media, cultural tourism, social media, higher education and other
fields [11].
3 Computer-Aided Translation and Interpretation Learning
Experiments
3.1 Effect Test Method
Effect test to select two natural classes (two class results, the number of close close), in
the process of experiment, the same teacher at the same multimedia network classroom,
respectively in the two class teaching content is the same, different teaching strate-
gies of teaching, the control class kept the traditional teaching, the experiment class in
interpreting teaching based on the technology of computer aided translation.
Application of Computer-Aided Translation in Interpretation Learning 637
3.2 Knowledge Level Test Paper
Before the implementation, the students in the experimental class and control class were
tested. The pre-test papers related to interpretation learning were made according to the
content of the interpreting textbooks and used to measure the initial level of students.
The topic of the post-test paper is related to interpretation learning.
3.3 Questionnaire Design
Based on the existing domestic and foreign research results on computer-assisted inter-
pretation in colleges and universities and the learning psychology theory of college stu-
dents, this study elaborately designed a questionnaire, which closely revolves around the
current situation of computer-assisted interpretation in colleges and universities in China.
The questionnaire is divided into three parts: the explanatory words of the questionnaire,
which explain the purpose of the survey, and make a promise of confidentiality; In the
main part of the questionnaire, the interviewees were asked to give feedback on the basic
situation of computer-aided interpretation teaching in their colleges and universities.
After soliciting the opinions of relevant experts, the structure, content, language
expression and other aspects of the questionnaire were revised and improved for many
times. After the preliminary questionnaire is formed, objective examination method is
adopted, students of our school are selected to conduct a small-scale pre-survey, and then
the questionnaire is simply tested for reliability. The questionnaire is further adjusted
and modified according to the problems in the pre-survey, and finally the questionnaire
is determined.
3.4 Reliability Analysis of the Questionnaire
This article uses Cronbach’s αcoefficient to test the internal consistency of the ques-
tionnaire. From a statistical point of view, the reliability coefficient of any test or scale
is above 0.70, indicating that the internal consistency of the test or scale is good, and
that the questionnaire has high internal consistency. The reliability analysis formula is
as follows:
rtt =2rhh
(1+rhh)(1)
a=(
k
k−1)∗(1−(Si2
ST 2)) (2)
Cronbach’s αcoefficient of the questionnaire in this paper is 0.921, indicating that
the questionnaire in this paper has a high internal consistency.
4 Experimental Results and Analysis
4.1 A Pretest Scores
The purpose of this paper is to find out whether the computer-aided translation can
promote learners’ interpreting training and thus improve the interpreting performance
638 R. Gui
Table 1. Independent Samples Test of Pretest Part
FSig
Part 1 Equal variances assumed 2.031 0.159
Part 2 1.237 0.279
Part 3 2.175 0.152
Fig. 1. Independent Samples Test of Pretest Part
of the test subjects. In the pre-test, the experimental group and the control group were
given the same test at the same time. The participants were randomly divided into several
groups. Through data analysis, we can find that there is no significant difference in their
performance in parts 1, 2 and 3 of the pre-test.
AsshowninTable1and Fig. 1, it is clear from the above analysis that there was no
significant difference in the performance of the testers during the pre-test. Specifically,
if the Pretest Part 1 score is placed within the 95% confidence interval of the difference,
the significance is 0.159 (BBB 0.05), which means that the null hypothesis is accepted.
In other words, there was no significant difference between the experimental group and
the control group in consecutive interpretation (part 1) before the course and training. In
pretest part 2, the significance was 0.279 (BBB 0.05). There was no significant difference
between the experimental group and the control group in the performance of consecutive
interpretation before the course and training. The significance of pretest part 3 was
0.152(BBB 0.05). In this regard, we also need to accept the null hypothesis that there is
no significant difference between the experimental group and the control group in the
performance of consecutive interpretation before the course and training.
Data analysis showed that in the pre-test stage, there was no significant differ-
ence between the two groups. The performance difference between the experimental
group and the control group was statistically significant. After that, the participants
went through a 10-week course and related self-training.
Application of Computer-Aided Translation in Interpretation Learning 639
Fig. 2. Independent Samples Test of Posttest Part
4.2 After the Test Result
AsshowninFig.2, it is obvious that there are significant differences in the performance
of participants in the post-test. Specifically, if the Posttest Part 1 score is placed below the
95% confidence interval for the difference, the significance is 0.023(<0.05), rejecting
the null hypothesis. That is to say, after the course and training, there is a significant
difference between the experimental group and the control group in the performance
of consecutive interpretation (Part I). The significance of Pretest Part 2 was 0.041 <
0.05. Here, the author needs to deny the null hypothesis, that is, there is a significant
difference between the experimental group and the control group in the results of con-
secutive interpretation (Part 3) after courses and training. The significance of Pretest
Part 3 was 0.029(<0.05). In this regard, we need to deny the null hypothesis that there
is a significant difference between the experimental group and the control group in the
results of consecutive interpretation (Part 3) after courses and training.
5 Conclusions
Computer-aided translation software can provide solutions to strengthen interpretation
classroom teaching and support students’ autonomous learning, and can also make the
connection between classroom work and autonomous learning closer. The results of the
experimental group were greatly affected by the application of computer-aided trans-
lation. After a 10-week course and subsequent interpreting training, all participants in
both the experimental and control groups improved their interpreting scores. Through
data analysis, we found that before the course and training, the two groups were at the
same level, but after the course and training, the experimental group was significantly
better than the control group. Given that the independent variable of this study is the use
of computer-aided translation software and the dependent variable is performance, it is
safe to say that the use of CAIT software improves the interpreting performance of the
subjects to a large extent.
640 R. Gui
Acknowledgements. This work was financially supported by Nanchang Institute of Technology
Teaching Reform Project: An Empirical Study of Blended Interpretation Teaching Mode under
the Background of “Internet Plus” Project No. 2020JG043.
References
1. Christensen TP, Schjoldager A (2016) Computer-aided translation tools – the uptake and use
by Danish translation service providers. J Spec Transl 25:89–105
2. Karpi´nska P (2017) Computer aided translation – possibilities, limitations and changes in the
field of professional translation. J Educ Cult Soc 8(2):133–142
3. Brihaye T, Geeraerts G, Ho H-M, Monmege B (2017) MightyL: a compositional translation
from MITL to timed automata. In: Majumdar R, Kunˇcak V (eds) CAV 2017, vol 10426.
LNCS. Springer, Cham, pp 421–440. https://doi.org/10.1007/978-3-319-63387-9_21
4. Li J, Zhang X, Jia C et al (2020) Direct speech-to-image translation. IEEE J Sel Top Sig
Process 14(3):517–529
5. Yao S (2017) Application of computer-aided translation in English teaching. Int J Emerg
Technol Learn (iJET) 12(08):105–117
6. Khan AM, Rahim N, Yousufi M (2021) China factor in the Sudan crisis: a politico-economic
perspective. J Lib Arts Sci 4(2):320–330
7. Penprase B (2016) New liberal arts and sciences institutions in India and Singapore: the role
of STEM education. In: Kirby WC, van der Wende MC (eds) Experiences in liberal arts and
science education from America, Europe, and Asia. Palgrave Macmillan US, New York, pp
61–73. https://doi.org/10.1057/978-1-349-94892-5_5
8. Wu H (2021) Multimedia interaction-based computer-aided translation technology in applied
English teaching. Mob Inf Syst 2021(5):1–10
9. Wang X (2021) Building a parallel corpus for English translation teaching based on computer-
aided translation software. Comput Aided Des Appl 18(S4):175–185
10. Excell D (2019) Some challenges in using computer-aided translation tools to facilitate second
language fluency in education. Ann Emerg Technol Comput 32:22–31
11. Xu X (2019) Research methods and applications of computer aided translation in paper mills.
Paper Asia 2(1):100–103
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-
NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/),
which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any
medium or format, as long as you give appropriate credit to the original author(s) and the source,
provide a link to the Creative Commons license and indicate if changes were made.
The images or other third party material in this chapter are included in the chapter’s Creative
Commons license, unless indicated otherwise in a credit line to the material. If material is not
included in the chapter’s Creative Commons license and your intended use is not permitted by
statutory regulation or exceeds the permitted use, you will need to obtain permission directly from
the copyright holder.
