Demi Guo, Yoon Kim, Alexander Rush
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.
Despite their empirical success, neural networks still have difficulty capturing compositional aspects of natural language. This work proposes a simple data augmentation approach to encourage compositional behavior in neural models for sequence-to-sequence problems. Our approach, SeqMix, creates new synthetic examples by softly combining input/output sequences from the training set. We connect this approach to existing techniques such as SwitchOut (Wang et al., 2018) and word dropout (Sennrich et al., 2016), and show that these techniques are all approximating variants of a single objective. SeqMix consistently yields approximately 1.0 BLEU improvement on five different translation datasets over strong Transformer baselines. On tasks that require strong compositional generalization such as SCAN and semantic parsing, Se-qMix also offers further improvements.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2011.09039")
get_code_for_paper("2011.09039")
have("2011.09039")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2011.09039.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2011.09039)
Connect an agent — have() is free.