Bing Qin, Xiaocheng Feng, Yichong Huang, Xinwei Geng
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.
Although all-in-one-model multilingual neural machine translation (MNMT) has achieved remarkable progress, the convergence inconsistency in the joint training is ignored, i.e.,different language pairs reaching convergence in different epochs. This leads to the trained MNMT model over-fitting low-resource language translations while under-fitting highresource ones. In this paper, we propose a novel training strategy named LSSD (Language-Specific Self-Distillation), which can alleviate the convergence inconsistency and help MNMT models achieve the best performance on each language pair simultaneously. Specifically, LSSD picks up language-specific best checkpoints for each language pair to teach the current model on the fly. Furthermore, we systematically explore three sample-level manipulations of knowledge transferring. Experimental results on three datasets show that LSSD obtains consistent improvements towards all language pairs and achieves the state-of-the-art 1 .
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2205.01620")
get_code_for_paper("2205.01620")
have("2205.01620")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2205.01620.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2205.01620)
Connect an agent — have() is free.