We explore using multilingual document embeddings for nearest neighbor mining
of parallel data. Three document-level representations are investigated: (i)
document embeddings generated by simply averaging multilingual sentence
embeddings; (ii) a neural bag-of-words (BoW) document encoding model; (iii) a
hierarchical multilingual document encoder (HiDE) that builds on our
sentence-level model. The results show document embeddings derived from
sentence-level averaging are surprisingly effective for clean datasets, but
suggest models trained hierarchically at the document-level are more effective
on noisy data. Analysis experiments demonstrate our hierarchical models are
very robust to variations in the underlying sentence embedding quality. Using
document embeddings trained with HiDE achieves state-of-the-art performance on
United Nations (UN) parallel document mining, 94.9% P@1 for en-fr and 97.3% P@1
for en-es.

本研究利用多语言文本嵌入来对平行数据进行最近邻挖掘，通过三种不同的文本层级表示方法，发现用 HiDE 训练产生的文档嵌入结果表现最佳，达到了 UN 平行文档挖掘的最新成果。