Sentiment-based Candidate Selection for NMT

Sentiment-based Candidate Selection For NMT Alex Jones alexander.g.jones.23@dartmouth.edu Dartmouth College, Hanover, NH, 03755, United States Derry Tanti Wijaya wijaya@bu.edu Department of Computer Science, Boston University, Boston, MA, 02215, United States Abstract The proliferation of user-generated content (UGC)—e.g. social media posts, comments, and re- views—has motivated the development of NLP applications tailored to these types of informal texts. Prevalent among these applications have been sentiment analysis and machine transla- tion (MT). Grounded in the observation that UGC features highly idiomatic, sentiment-charged language, we propose a decoder-side approach that incorporates automatic sentiment scoring into the MT candidate selection process. We train monolingual sentiment classifiers in English and Spanish, in addition to a multilingual sentiment model, by fine-tuning BERT and XLM- RoBERTa. Using n-best candidates generated by a baseline MT model with beam search, we select the candidate that minimizes the absolute difference between the sentiment score of the source sentence and that of the translation, and perform two human evaluations to assess the produced translations. Unlike previous work, we select this minimally divergent translation by considering the sentiment scores of the source sentence and translation on a continuous in- terval, rather than using e.g. binary classification, allowing for more fine-grained selection of translation candidates. The results of human evaluations show that, in comparison to the open- source MT baseline model on top of which our sentiment-based pipeline is built, our pipeline produces more accurate translations of colloquial, sentiment-charged source texts1. 1 Introduction The Web, widespread internet access, and social media have transformed the way people cre- ate, consume, and share content, resulting in the proliferation of user-generated content (UGC). UGC—such as social media posts, comments, and reviews—has proven to be of paramount importance both for users and organizations/institutions (Pozzi et al., 2016). As users enjoy the freedoms of sharing their opinions in this relatively unconstrained environment, corporations can analyze user sentiments and extract insights for their decision-making processes, (Timo- shenko and Hauser, 2019) or translate UGC to other languages to widen the company’s scope and impact. For example, Hale (2016) shows that translating UGC between certain language pairs has beneficial effects on the overall ratings customers gave to attractions and shows on Tri- pAdvisor, while the absence of translation hurts ratings. However, translating UGC comes with its own challenges that differ from those of translating well-formed documents like news arti- cles. UGC is shorter and noisier, characterized by idiomatic and colloquial expressions (Pozzi et al., 2016). Translating idiomatic expressions is hard, as they often convey figurative meaning that cannot be reconstructed from the meaning of their parts (Wasow et al., 1983), and remains one of the open challenges in machine translation (MT) (Fadaee et al., 2018). Idiomatic ex- pressions, however, typically carry an additional property: they imply an affective stance rather 1Code and reference materials are available at https://github.com/AlexJonesNLP/SentimentMT Proceedings of the 18th Biennial Machine Translation Summit Virtual USA, August 16 - 20, 2021, Volume 1: MT Research Track Page 188 than a neutral one (Wasow et al., 1983). The sentiment of …

Content truncated to 500 words