Tong Xiao, Hui Liu, Bei Li, Jingbo Zhu, Tongran Liu, Ziyang Wang, Yufan Jiang, Changliang Li
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.
In encoder-decoder neural models, multiple encoders are in general used to represent the contextual information in addition to the individual sentence. In this paper, we investigate multi-encoder approaches in document-level neural machine translation (NMT). Surprisingly, we find that the context encoder does not only encode the surrounding sentences but also behaves as a noise generator. This makes us rethink the real benefits of multi-encoder in context-aware translation -some of the improvements come from robust training. We compare several methods that introduce noise and/or well-tuned dropout setup into the training of these encoders. Experimental results show that noisy training plays an important role in multi-encoder-based NMT, especially when the training data is small. Also, we establish a new state-of-the-art on IWSLT Fr-En task by careful use of noise generation and dropout methods.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2005.03393")
get_code_for_paper("2005.03393")
have("2005.03393")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2005.03393.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2005.03393)
Connect an agent — have() is free.