Homographs, words with the same spelling but different meanings, remain challenging in Neural Machine Translation (NMT). While recent works leverage various word embedding approaches to differentiate word sense in NMT, they do not focus on the pivotal components in resolving ambiguities of homographs in NMT: the hidden states of an encoder. In this paper, we propose a novel approach to tackle homographic issues of NMT in the latent space. We first train an encoder (aka "HDR-encoder") to learn universal sentence representations in a natural language inference (NLI) task. We further fine-tune the encoder using homograph-based synset sentences from WordNet, enabling it to learn word-level homographic disambiguation representations (HDR). The pre-trained HDR-encoder is subsequently integrated with a transformer-based NMT in various schemes to improve translation accuracy. Experiments on four translation directions demonstrate the effectiveness of the proposed method in enhancing the performance of NMT systems in the BLEU scores (up to +2.3 compared to a solid baseline). The effects can be verified by other metrics (F1, precision, and recall) of translation accuracy in an additional disambiguation task. Visualization methods like heatmaps, T-SNE and translation examples are also utilized to demonstrate the effects of the proposed method.

翻译：同形异义词（拼写相同但含义不同的词语）在神经机器翻译（NMT）中仍然构成挑战。尽管近期研究利用多种词嵌入方法来区分NMT中的词义，但这些方法并未聚焦于解决NMT中同形异义词歧义的关键组件：编码器的隐藏状态。本文提出一种新颖方法，在潜在空间中处理NMT的同形异义问题。我们首先训练一个编码器（称为"HDR-encoder"），使其在自然语言推理（NLI）任务中学习通用句子表示。随后，使用WordNet中基于同形异义词集的句子对该编码器进行微调，使其能够学习词级同形异义词消歧表示（HDR）。预训练后的HDR-encoder以多种方案与基于Transformer的NMT集成，以提升翻译准确性。在四个翻译方向上的实验表明，该方法能有效提升NMT系统的BLEU分数（相比强基线最高提升+2.3）。在附加消歧任务中，其他翻译准确性指标（F1、精确率、召回率）亦可验证其效果。我们同时采用热力图、T-SNE和翻译示例等可视化方法，展示了所提方法的效果。