The repetition of words in an English sentence can create a monotonous or awkward impression. In such cases, repetition should be avoided appropriately. To evaluate the performance of machine translation (MT) systems in avoiding such repetition and outputting more polished translations, we presented the shared task of controlling the lexical choice of MT systems. From Japanese–English parallel news articles, we collected several hundred sentence pairs in which the source sentences containing repeated words were translated in a style that avoided repetition. Participants were required to encourage the MT system to output tokens in a non-repetitive manner while maintaining translation quality. We conducted human and automatic evaluations of systems submitted by two teams based on an encoder-decoder Transformer and a large language model, respectively. From the experimental results and analysis, we report a series of findings on this task.

This paper presents the results of the shared tasks from the 10th workshop on Asian translation (WAT2023). For the WAT2023, 2 teams submitted their translation results for the human evaluation. We also accepted 1 research paper. About 40 translation results were submitted to the automatic evaluation server, and selected submissions were manually evaluated.

This paper describes the system of our team (NHK) for the WAT 2021 Japanese-English restricted machine translation task. In this task, the aim is to improve quality while maintaining consistent terminology for scientific paper translation. This task has a unique feature, where some words in a target sentence are given in addition to a source sentence. In this paper, we use a lexically-constrained neural machine translation (NMT), which concatenates the source sentence and constrained words with a special token to input them into the encoder of NMT. The key to the successful lexically-constrained NMT is the way to extract constraints from a target sentence of training data. We propose two extraction methods: proper-noun constraint and mistranslated-word constraint. These two methods consider the importance of words and fallibility of NMT, respectively. The evaluation results demonstrate the effectiveness of our lexical-constraint method.

This paper describes the system of the NHK-NES team for the WAT 2020 Japanese–English newswire task. There are two main problems in Japanese-English news translation: translation of dropped subjects and compatibility between equivalent translations and English news-style outputs. We address these problems by extracting subjects from the context based on predicate-argument structures and using them as additional inputs, and constructing parallel Japanese-English news sentences equivalently translated from English news sentences. The evaluation results confirm the effectiveness of our context-utilization method.