Davis Liang, Peng Xu, Bing Xiang, Zhiheng Huang
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.
Transformer architectures rely on explicit position encodings in order to preserve a notion of word order. In this paper, we argue that existing work does not fully utilize position information. For example, the initial proposal of a sinusoid embedding is fixed and not learnable. In this paper, we first review absolute position embeddings and existing methods for relative position embeddings. We then propose new techniques that encourage increased interaction between query, key and relative position embeddings in the self-attention mechanism. Our most promising approach is a generalization of the absolute position embedding, improving results on SQuAD1.1 compared to previous position embeddings approaches. In addition, we address the inductive property of whether a position embedding can be robust enough to handle long sequences. We demonstrate empirically that our relative position embedding method is reasonably generalized and robust from the inductive perspective. Finally, we show that our proposed method can be adopted as a near drop-in replacement for improving the accuracy of large models with a small computational budget.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2009.13658")
get_code_for_paper("2009.13658")
have("2009.13658")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2009.13658.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2009.13658)
Connect an agent — have() is free.