Dongyan Zhao, Rui Yan, Lemao Liu, Xin Cheng, Shen Gao
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.
Retrieval-augmented Neural Machine Translation models have been successful in many translation scenarios. Different from previous works that make use of mutually similar but redundant translation memories (TMs), we propose a new retrieval-augmented NMT to model contrastively retrieved translation memories that are holistically similar to the source sentence while individually contrastive to each other providing maximal information gains in three phases. First, in TM retrieval phase, we adopt a contrastive retrieval algorithm to avoid redundancy and uninformativeness of similar translation pieces. Second, in memory encoding stage, given a set of TMs we propose a novel Hierarchical Group Attention module to gather both local context of each TM and global context of the whole TM set. Finally, in training phase, a Multi-TM contrastive learning objective is introduced to learn salient feature of each TM with respect to target sentence. Experimental results show that our framework obtains improvements over strong baselines on the benchmark datasets.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2212.03140")
get_code_for_paper("2212.03140")
have("2212.03140")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2212.03140.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2212.03140)
Connect an agent — have() is free.