Improved statistical machine translation using monolingual paraphrases
This addresses data scarcity for machine translation practitioners, but it is incremental as it builds on existing statistical methods.
The paper tackled the problem of limited training data for statistical machine translation by proposing a monolingual paraphrasing method to augment data without needing additional aligned data, resulting in an improvement equivalent to 33%-50% of doubling the training data.
We propose a novel monolingual sentence paraphrasing method for augmenting the training data for statistical machine translation systems "for free" -- by creating it from data that is already available rather than having to create more aligned data. Starting with a syntactic tree, we recursively generate new sentence variants where noun compounds are paraphrased using suitable prepositions, and vice-versa -- preposition-containing noun phrases are turned into noun compounds. The evaluation shows an improvement equivalent to 33%-50% of that of doubling the amount of training data.