Sequence to Sequence Mixture Model for Diverse Machine Translation
This addresses the issue of translation diversity for machine translation users, though it is an incremental improvement over existing methods.
The paper tackled the problem of limited diversity in sequence-to-sequence machine translation models by developing a sequence-to-sequence mixture (S2SMIX) model that uses a committee of specialized models to improve both translation diversity and quality, with experiments on four language pairs showing superiority over baselines.
Sequence to sequence (SEQ2SEQ) models often lack diversity in their generated translations. This can be attributed to the limitation of SEQ2SEQ models in capturing lexical and syntactic variations in a parallel corpus resulting from different styles, genres, topics, or ambiguity of the translation process. In this paper, we develop a novel sequence to sequence mixture (S2SMIX) model that improves both translation diversity and quality by adopting a committee of specialized translation models rather than a single translation model. Each mixture component selects its own training dataset via optimization of the marginal loglikelihood, which leads to a soft clustering of the parallel corpus. Experiments on four language pairs demonstrate the superiority of our mixture model compared to a SEQ2SEQ baseline with standard or diversity-boosted beam search. Our mixture model uses negligible additional parameters and incurs no extra computation cost during decoding.