Tag Assisted Neural Machine Translation of Film Subtitles

Proceedings of the 18th International Conference on Spoken Language Translation, pages 255–262 Bangkok, Thailand (Online), August 5–6, 2021. ©2021 Association for Computational Linguistics 255 Tag Assisted Neural Machine Translation of Film Subtitles Aren Siekmeier∗, WonKee Lee∗, Hongseok Kwon†, and Jong-Hyeok Lee∗† Pohang University of Science and Technology ∗Department of Computer Science and Engineering †Graduate School of Artificial Intelligence {asiekmeier,wklee,hkwon,jhlee}@postech.ac.kr Abstract We implemented a neural machine translation system that uses automatic sequence tagging to improve the quality of translation. Instead of operating on unannotated sentence pairs, our system uses pre-trained tagging systems to add linguistic features to source and target sentences. Our proposed neural architecture learns a combined embedding of tokens and tags in the encoder, and simultaneous token and tag prediction in the decoder. Compared to a baseline with unannotated training, this architecture increased the BLEU score of Ger- man to English film subtitle translation outputs by 1.61 points using named entity tags; how- ever, the BLEU score decreased by 0.38 points using part-of-speech tags. This demonstrates that certain token-level tag outputs from off-the- shelf tagging systems can improve the output of neural translation systems using our com- bined embedding and simultaneous decoding extensions. 1 Introduction Neural machine translation (NMT) uses neural networks to translate unannotated text between a source and target language, but without additional linguistic information certain ambiguous inputs may be translated incorrectly. Consider the fol- lowing examples: 1) Titanic struggles between good and evil.  선과 악 사이의 엄청난 투쟁. big fight between good and evil  타이타닉은 선과 악 사이에서 투쟁 중이다. The Titanic is fighting between good and evil 2) Titanic struggles to stay afloat.  타이타닉은 침몰하지 않도록 고군분투 중이다. The Titanic is struggling not to sink  침몰하지 않기 위한 엄청난 투쟁. big fight not to sink In (1), “Titanic” is best translated as a common adjective; in (2), it most likely refers to a named entity, the famous ship. In addition to the bare token sequences, part-of-speech or named entity annotation of each token, provided manually or automatically, could provide additional information to improve the quality of translation. Natural language processing (NLP) tools have benefited from the same explosion in deep learning and neural network developments that has spurred NMT. NLP tools include part-of-speech (POS) tag- gers, identifying the syntactic function of each in- put token, and named entity recognition systems. Named entity recognition (NER) identifies which tokens refer to named entities, including proper nouns such as people, place names, organizations, or dates. Recently, automatic named entity recog- nition (NER) systems have seen much develop- ment and refinement with the same deep learning tools used for NMT (Li et al., 2020). Automatic neural NER systems have achieved accuracy ex- ceeding 92% F1 scores in many languages and do- mains (Wang et al., 2019; Akbik et al., 2018). NER tags produced by these systems are useful in many other natural language processing contexts, such as coreference resolution, entity linking, or entity extraction (Ferreira Cruz et al., 2020). POS tag- gers have also achieved …

Content truncated to 500 words