Metric Learning in Multilingual Sentence Similarity Measurement for Document Alignment
This work addresses document alignment for multilingual applications, but it is incremental as it applies an existing method (metric learning) to a known bottleneck in a specific domain.
The paper tackles the problem of document alignment using multilingual sentence representations by replacing unsupervised distance measurement techniques with supervised metric learning, showing that task-specific metrics outperform unsupervised ones on a dataset of English, Sinhala, and Tamil languages.
Document alignment techniques based on multilingual sentence representations have recently shown state of the art results. However, these techniques rely on unsupervised distance measurement techniques, which cannot be fined-tuned to the task at hand. In this paper, instead of these unsupervised distance measurement techniques, we employ Metric Learning to derive task-specific distance measurements. These measurements are supervised, meaning that the distance measurement metric is trained using a parallel dataset. Using a dataset belonging to English, Sinhala, and Tamil, which belong to three different language families, we show that these task-specific supervised distance learning metrics outperform their unsupervised counterparts, for document alignment.