In this paper, we present an approach to learn multilingual sentence
embeddings using a bi-directional dual-encoder with additive margin softmax.
The embeddings are able to achieve state-of-the-art results on the United
Nations (UN) parallel corpus retrieval task. In all the languages tested, the
system achieves P@1 of 86% or higher. We use pairs retrieved by our approach to
train NMT models that achieve similar performance to models trained on gold
pairs. We explore simple document-level embeddings constructed by averaging our
sentence embeddings. On the UN document-level retrieval task, document
embeddings achieve around 97% on P@1 for all experimented language pairs.
Lastly, we evaluate the proposed model on the BUCC mining task. The learned
embeddings with raw cosine similarity scores achieve competitive results
compared to current state-of-the-art models, and with a second-stage scorer we
achieve a new state-of-the-art level on this task.

本研究提出了一种使用双向双编码器和加性边际 softmax 学习多语言句子嵌入的方法，能够在联合国 (UN) 平行语料库检索任务上取得最先进的结果，并使用检索到的语言对训练 NMT 模型。通过对我们的句子嵌入平均构建的简单文档级别嵌入进行实验，能在 UN 文档级别检索任务中取得 97% 以上的 P@1。最后，我们在 BUCC 挖掘任务上评估了所提出的模型，利用原始余弦相似度得分的学习嵌入与当前最先进的模型相比取得了有竞争力的结果，并利用第二阶段的评分器在此任务上实现了新的最先进水平。