Isometric MT: Neural Machine Translation for Automatic Dubbing
This addresses the problem of maintaining translation quality while controlling output length for automatic dubbing, which is incremental as it improves upon prior two-step approaches.
The paper tackles the challenge of generating neural machine translation outputs that closely match the source length for automatic dubbing, introducing a self-learning approach called Isometric MT that directly learns to produce length-matched translations without needing multiple hypotheses or re-ranking. Results on four language pairs show it outperforms more complex existing methods in evaluations.
Automatic dubbing (AD) is among the machine translation (MT) use cases where translations should match a given length to allow for synchronicity between source and target speech. For neural MT, generating translations of length close to the source length (e.g. within +-10% in character count), while preserving quality is a challenging task. Controlling MT output length comes at a cost to translation quality, which is usually mitigated with a two step approach of generating N-best hypotheses and then re-ranking based on length and quality. This work introduces a self-learning approach that allows a transformer model to directly learn to generate outputs that closely match the source length, in short Isometric MT. In particular, our approach does not require to generate multiple hypotheses nor any auxiliary ranking function. We report results on four language pairs (English - French, Italian, German, Spanish) with a publicly available benchmark. Automatic and manual evaluations show that our method for Isometric MT outperforms more complex approaches proposed in the literature.