This paper introduces our neural machine translation system’s participation in the WAT 2022 shared translation task (team ID: sakura). We participated in the Parallel Data Filtering Task. Our approach based on Feature Decay Algorithms achieved +1.4 and +2.4 BLEU points for English to Japanese and Japanese to English respectively compared to the model trained on the full dataset, showing the effectiveness of FDA on in-domain data selection.
This paper introduces our neural machine translation systems’ participation in the WAT 2021 shared translation tasks (team ID: sakura). We participated in the (i) NICT-SAP, (ii) Japanese-English multimodal translation, (iii) Multilingual Indic, and (iv) Myanmar-English translation tasks. Multilingual approaches such as mBART (Liu et al., 2020) are capable of pre-training a complete, multilingual sequence-to-sequence model through denoising objectives, making it a great starting point for building multilingual translation systems. Our main focus in this work is to investigate the effectiveness of multilingual finetuning on such a multilingual language model on various translation tasks, including low-resource, multimodal, and mixed-domain translation. We further explore a multimodal approach based on universal visual representation (Zhang et al., 2019) and compare its performance against a unimodal approach based on mBART alone.
This paper introduces our neural machine translation systems’ participation in the WAT 2020 (team ID: goku20). We participated in the (i) Patent, (ii) Business Scene Dialogue (BSD) document-level translation, (iii) Mixed-domain tasks. Regardless of simplicity, standard Transformer models have been proven to be very effective in many machine translation systems. Recently, some advanced pre-training generative models have been proposed on the basis of encoder-decoder framework. Our main focus of this work is to explore how robust Transformer models perform in translation from sentence-level to document-level, from resource-rich to low-resource languages. Additionally, we also investigated the improvement that fine-tuning on the top of pre-trained transformer-based models can achieve on various tasks.
Recent question generation (QG) approaches often utilize the sequence-to-sequence framework (Seq2Seq) to optimize the log likelihood of ground-truth questions using teacher forcing. However, this training objective is inconsistent with actual question quality, which is often reflected by certain global properties such as whether the question can be answered by the document. As such, we directly optimize for QG-specific objectives via reinforcement learning to improve question quality. We design three different rewards that target to improve the fluency, relevance, and answerability of generated questions. We conduct both automatic and human evaluations in addition to thorough analysis to explore the effect of each QG-specific reward. We find that optimizing on question-specific rewards generally leads to better performance in automatic evaluation metrics. However, only the rewards that correlate well with human judgement (e.g., relevance) lead to real improvement in question quality. Optimizing for the others, especially answerability, introduces incorrect bias to the model, resulting in poorer question quality. The code is publicly available at https://github.com/YuxiXie/RL-for-Question-Generation.