Unsupervised Clustering of Commercial Domains for Adaptive Machine Translation
This work addresses domain adaptation for machine translation in commercial settings, but it is incremental as it compares existing distances without introducing new methods.
The paper tackled the problem of clustering commercial domains for adaptive machine translation by comparing five distances in hierarchical clustering on a benchmark of 40 domains, finding that the most expensive distance enabled good MT performance with few but highly populated clusters.
In this paper, we report on domain clustering in the ambit of an adaptive MT architecture. A standard bottom-up hierarchical clustering algorithm has been instantiated with five different distances, which have been compared, on an MT benchmark built on 40 commercial domains, in terms of dendrograms, intrinsic and extrinsic evaluations. The main outcome is that the most expensive distance is also the only one able to allow the MT engine to guarantee good performance even with few, but highly populated clusters of domains.