Shafiq Joty, Ai Aw, Weiwen Xu, Kui Wu, Yang Ding
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.
Neural Machine Translation (NMT) has achieved significant breakthrough in performance but is known to suffer vulnerability to input perturbations. As real input noise is difficult to predict during training, robustness is a big issue for system deployment. In this paper, we improve the robustness of NMT models by reducing the effect of noisy words through a Context-Enhanced Reconstruction (CER) approach. CER trains the model to resist noise in two steps: (1) perturbation step that breaks the naturalness of input sequence with madeup words; (2) reconstruction step that defends the noise propagation by generating better and more robust contextual representation. Experimental results on Chinese-English (ZH-EN) and French-English (FR-EN) translation tasks demonstrate robustness improvement on both news and social media text. Further finetuning experiments on social media text show our approach can converge at a higher position and provide a better adaptation.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2104.09810")
get_code_for_paper("2104.09810")
have("2104.09810")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2104.09810.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2104.09810)
Connect an agent — have() is free.