Sentiment Aware Neural Machine Translation

Si, Chenglei; Wu, Kui; Aw, Ai Ti; Kan, Min-Yen

doi:10.18653/v1/d19-5227

Cited by 9 publications

(11 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To evaluate the effect of sentiment, we conduct some experiments on several baselines including single-modality ones and double-modality ones. In terms of implementation, following Si et al (2019), we append the sentiment label to the head of the source utterance. Tab.…”

Section: Effect Of Sentiment On Multimodal Chat Translationmentioning

confidence: 99%

MSCTD: A Multimodal Sentiment Chat Translation Dataset

Liang¹,

Meng²,

Xu³

et al. 2022

Preprint

View full text Add to dashboard Cite

Multimodal machine translation and textual chat translation have received considerable attention in recent years. Although the conversation in its natural form is usually multimodal, there still lacks work on multimodal machine translation in conversations. In this work, we introduce a new task named Multimodal Chat Translation (MCT), aiming to generate more accurate translations with the help of the associated dialogue history and visual context. To this end, we firstly construct a Multimodal Sentiment Chat Translation Dataset (MSCTD) containing 142,871 English-Chinese utterance pairs in 14,762 bilingual dialogues and 30,370 English-German utterance pairs in 3,079 bilingual dialogues. Each utterance pair, corresponding to the visual context that reflects the current conversational scene, is annotated with a sentiment label. Then, we benchmark the task by establishing multiple baseline systems that incorporate multimodal and sentiment features for MCT. Preliminary experiments on four language directions (English↔Chinese and English↔German) verify the potential of contextual and multimodal information fusion and the positive impact of sentiment on the MCT task. Additionally, as a by-product of the MSCTD, it also provides two new benchmarks on multimodal dialogue sentiment analysis. Our work can facilitate research on both multimodal chat translation and multimodal dialogue sentiment analysis. 1

show abstract

Section: Effect Of Sentiment On Multimodal Chat Translationmentioning

confidence: 99%

MSCTD: A Multimodal Sentiment Chat Translation Dataset

Liang¹,

Meng²,

Xu³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Lohar et al (2017) build separate translation models for data coming from each sentiment category. Si et al (2019) directly incorporate sentiment in their neural MT system, implementing a Seq2Seq English-to-Chinese translation model that keeps not only the semantics but also the sentiment of input text, both by including the sentiment label in source sentences, and by learning the negative/positive meanings of the ambiguous word as separate embeddings.…”

Section: Related Workmentioning

confidence: 99%

Lost in Back-Translation: Emotion Preservation in Neural Machine Translation

Troiano

Klinger

Padó

2020

Proceedings of the 28th International Conference on Computational Linguistics

View full text Add to dashboard Cite

Machine translation provides powerful methods to convert text between languages, and is therefore a technology enabling a multilingual world. An important part of communication, however, takes place at the non-propositional level (e.g., politeness, formality, emotions), and it is far from clear whether current MT methods properly translate this information.This paper investigates the specific hypothesis that the non-propositional level of emotions is at least partially lost in MT. We carry out a number of experiments in a back-translation setup and establish that (1) emotions are indeed partially lost during translation; (2) this tendency can be reversed almost completely with a simple re-ranking approach informed by an emotion classifier, taking advantage of diversity in the n-best list; (3) the re-ranking approach can also be applied to change emotions, obtaining a model for emotion style transfer. An in-depth qualitative analysis reveals that there are recurring linguistic changes through which emotions are toned down or amplified, such as change of modality.

show abstract

“…They attempt to strike a balance between improving sentiment transfer and preserving translation accuracy as measured by evaluative metrics such as BLEU and METEOR (Lohar et al, 2018). A similar technique is used by Si et al (2019) as they build a valence sensitive NMT model for the translation of ambiguous words that can have different polarities in different contexts. Each input sentence is annotated with a positive or negative label to indicate its polarity.…”

Section: Related Workmentioning

confidence: 99%

“…Each input sentence is annotated with a positive or negative label to indicate its polarity. They show that adding this tag to the source sentence at the training time and creating dual polarity embedding vectors for ambiguous words can improve sentiment transfer at the word level (Si et al, 2019).…”

Section: Related Workmentioning

confidence: 99%

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

Saadany¹,

Orăsan²

2020

Preprint

View full text Add to dashboard Cite

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.

show abstract

Sentiment Aware Neural Machine Translation

Cited by 9 publications

References 16 publications

MSCTD: A Multimodal Sentiment Chat Translation Dataset

MSCTD: A Multimodal Sentiment Chat Translation Dataset

Lost in Back-Translation: Emotion Preservation in Neural Machine Translation

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

Contact Info

Product

Resources

About