Measuring Sentiment Bias in Machine Translation

被引：1

作者：

Hartung, Kai ^{[1
]}

Herygers, Aaricia ^{[1
]}

Kurlekar, Shubham Vijay ^{[1
]}

Zakaria, Khabbab ^{[1
]}

Volkan, Taylan ^{[1
]}

Groettrup, Soeren ^{[1
]}

Georges, Munir ^{[1
,2
]}

机构：

[1] TH Ingolstadt, AImot Bavaria, Ingolstadt, Germany

[2] Intel Labs, Munich, Germany

来源：

TEXT, SPEECH, AND DIALOGUE, TSD 2023 | 2023年 / 14102卷

关键词：

Machine translation; sentiment classification; bias;

D O I：

10.1007/978-3-031-40498-6_8

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Biases induced to text by generative models have become an increasingly large topic in recent years. In this paper we explore how machine translation might introduce a bias in sentiments as classified by sentiment analysis models. For this, we compare three open access machine translation models for five different languages on two parallel corpora to test if the translation process causes a shift in sentiment classes recognized in the texts. Though our statistic test indicate shifts in the label probability distributions, we find none that appears consistent enough to assume a bias induced by the translation process.

引用

页码：82 / 93

页数：12

共 50 条

[1] Investigating the roles of sentiment in machine translation
Mahata, Sainik Kumar
Das, Dipankar
Bandyopadhyay, Sivaji
MACHINE TRANSLATION, 2021, 35 (04) : 687 - 709
[2] Gender Bias in Machine Translation
Savoldi, Beatrice
Gaido, Marco
Bentivogli, Luisa
Negri, Matteo
Turchi, Marco
TRANSACTIONS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, 2021, 9 : 845 - 874
[3] Gender bias in machine learning for sentiment analysis
Thelwall, Mike
ONLINE INFORMATION REVIEW, 2018, 42 (03) : 343 - 354
[4] Uses of Machine Translation in the Sentiment Analysis of Tweets
Peisenieks, Janis
Skadins, Raivis
HUMAN LANGUAGE TECHNOLOGIES - THE BALTIC PERSPECTIVE, BALTIC HLT 2014, 2014, 268 : 126 - 131
[5] Evaluating Gender Bias in Machine Translation
Stanovsky, Gabriel
Smith, Noah A.
Zettlemoyer, Luke
57TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2019), 2019, : 1679 - 1684
[6] Machine Translation for Machines: the Sentiment Classification Use Case
Tebbifakhr, Amirhossein
Bentivogli, Luisa
Negri, Matteo
Turchi, Marco
2019 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING AND THE 9TH INTERNATIONAL JOINT CONFERENCE ON NATURAL LANGUAGE PROCESSING (EMNLP-IJCNLP 2019): PROCEEDINGS OF THE CONFERENCE, 2019, : 1368 - 1374
[7] Sentiment Analysis for Turkish Unstructured Data by Machine Translation
Yildirim, Mustafa
Okay, Feyza Yildirim
Ozdemir, Suat
2020 IEEE INTERNATIONAL CONFERENCE ON BIG DATA (BIG DATA), 2020, : 4811 - 4817
[8] Bias Mitigation in Machine Translation Quality Estimation
Behnke, Hanna
Fomicheva, Marina
Specia, Lucia
PROCEEDINGS OF THE 60TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2022), VOL 1: (LONG PAPERS), 2022, : 1475 - 1487
[9] On the Language Coverage Bias for Neural Machine Translation
Wang, Shuo
Tu, Zhaopeng
Tan, Zhixing
Shi, Shuming
Sun, Maosong
Liu, Yang
FINDINGS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, ACL-IJCNLP 2021, 2021, : 4778 - 4790
[10] Reference Bias in Monolingual Machine Translation Evaluation
Fomicheva, Marina
Specia, Lucia
PROCEEDINGS OF THE 54TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2016), VOL 2, 2016, : 77 - 82

← 1 2 3 4 5 →