Please use this identifier to cite or link to this item:
Title: Sentiment Aware Neural Machine Translation
Authors: Chenglei Si
Kui Wu
Ai Ti Aw
Min-Yen Kan 
Issue Date: 2019
Publisher: Association for Computational Linguistics
Citation: Chenglei Si, Kui Wu, Ai Ti Aw, Min-Yen Kan (2019). Sentiment Aware Neural Machine Translation. Proceedings of the 6th Workshop on Asian Translation : 200-206. ScholarBank@NUS Repository.
Abstract: Sentiment ambiguous lexicons refer to words where their polarity depends strongly on context. As such, when the context is absent, their translations or their embedded sentence ends up (incorrectly) being dependent on the training data. While neural machine translation (NMT) has achieved great progress in recent years, most systems aim to produce one single correct translation for a given source sentence. We investigate the translation variation in two sentiment scenarios. We perform experiments to study the preservation of sentiment during translation with three different methods that we propose. We conducted tests with both sentiment and non-sentiment bearing contexts to examine the effectiveness of our methods. We show that NMT can generate both positive- and negative-valent translations of a source sentence, based on a given input sentiment label. Empirical evaluations show that our valence-sensitive embedding (VSE) method significantly outperforms a sequenceto-sequence (seq2seq) baseline, both in terms of BLEU score and ambiguous word translation accuracy in test, given non-sentiment bearing contexts.
Source Title: Proceedings of the 6th Workshop on Asian Translation
DOI: 10.18653/v1/D19-5227
Appears in Collections:Elements
Staff Publications

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
D19-5227.pdf413.29 kBAdobe PDF



Page view(s)

checked on Oct 15, 2020

Google ScholarTM



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.