We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Subword units are an effective way to alleviate the open vocabulary problems in neural machine translation (NMT). While sentences are usually converted into unique subword sequences, subword segmentation is potentially ambiguous and multiple segmentations are possible even with the same vocabulary. The question addressed in this paper is whether it is possible to harness the segmentation ambiguity as a noise to improve the robustness of NMT. We present a simple regularization method, subword regularization, which trains the model with multiple subword segmentations probabilistically sampled during training. In addition, for better subword sampling, we propose a new subword segmentation algorithm based on a unigram language model. We experiment with multiple corpora and report consistent improvements especially on low resource and out-of-domain settings.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("1804.10959")
get_code_for_paper("1804.10959")
have("1804.10959")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/1804.10959.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/1804.10959)
Connect an agent — have() is free.