Is it Great or Terrible? Preserving Sentiment in Neural Machine Translation of Arabic Reviews

Abstract

Since the advent of Neural Machine Translation (NMT) approaches there has been a tremendous improvement in the quality of automatic translation. However, NMT output still lacks accuracy in some low-resource languages and sometimes makes major errors that need extensive postediting. This is particularly noticeable with texts that do not follow common lexico-grammatical standards, such as user generated content (UGC). In this paper we investigate the challenges involved in translating book reviews from Arabic into English, with particular focus on the errors that lead to incorrect translation of sentiment polarity. Our study points to the special characteristics of Arabic UGC, examines the sentiment transfer errors made by Google Translate of Arabic UGC to English, analyzes why the problem occurs, and proposes an error typology specific of the translation of Arabic UGC. Our analysis shows that the output of online translation tools of Arabic UGC can either fail to transfer the sentiment at all by producing a neutral target text, or completely flips the sentiment polarity of the target word or phrase and hence delivers a wrong affect message. We address this problem by fine-tuning an NMT model with respect to sentiment polarity showing that this approach can significantly help with correcting sentiment errors detected in the online translation of Arabic UGC.

Applications and Challenges of Sentiment Analysis in Real-life Scenarios

“…Translation: The translation of sentiment is a known problem within the deep learning-based translation models. Much research has shown that perturbing the input to such translation models, i.e., reversing the polarity or the sentiment carried by the original input sentence results in incorrect output translation where the correct sentiment or polarity (especially negation) is not carried forward (Salameh et al, 2015;Mohammad et al, 2016;Hossain et al, 2020;Saadany and Orasan, 2020;Kanojia et al, 2021;Saadany et al, 2021;Tang et al, 2021) including research from statistical machine translation era (Wetzel and Bond, 2012). Interpreting: Carstensen and Dahlberg (2017) argue how interpreting during a court session, i.e., legal interpreting required the use of emotions by human interpreters to make it better.…”