Mohammad Norouzi, William Chan, Saurabh Saxena, Chitwan Saharia
We lifted 2 functions out of this paper's own repositories and ran 1 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| m3yrin/aligned-cross-entropy | reimplementation | 1 of 1 |
| m3yrin/nar-latent-alignment | pwc_unofficial | 0 of 1 |
| Function | Status | Where it lives |
|---|---|---|
| axe_loss | Ran | m3yrin/aligned-cross-entropy/axe/axe.py code served (permissive licence) · get_code("c65e558a970ba300") |
| sequence_ctc_loss_with_logits | Not yet run | m3yrin/nar-latent-alignment/src/utils/loss.py code served (permissive licence) · get_code("614ba3852c0598c1") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
This paper presents two strong methods, CTC and Imputer, for non-autoregressive machine translation that model latent alignments with dynamic programming. We revisit CTC for machine translation and demonstrate that a simple CTC model can achieve state-of-theart for single-step non-autoregressive machine translation, contrary to what prior work indicates. In addition, we adapt the Imputer model for non-autoregressive machine translation and demonstrate that Imputer with just 4 generation steps can match the performance of an autoregressive Transformer baseline. Our latent alignment models are simpler than many existing non-autoregressive translation baselines; for example, we do not require target length prediction or re-scoring with an autoregressive model. On the competitive WMT'14 En→De task, our CTC model achieves 25.7 BLEU with a single generation step, while Imputer achieves 27.5 BLEU with 2 generation steps, and 28.0 BLEU with 4 generation steps. This compares favourably to the autoregressive Transformer baseline at 27.8 BLEU. * Equal contribution. † Work done as part of the Google AI Residency.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2004.07437")
get_code_for_paper("2004.07437")
have("2004.07437")
Connect an agent — have() is free.