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.
We propose a simple yet robust stochastic answer network (SAN) that simulates multi-step reasoning in machine reading comprehension. Compared to previous work such as ReasoNet which used reinforcement learning to determine the number of steps, the unique feature is the use of a kind of stochastic prediction dropout on the answer module (final layer) of the neural network during the training. We show that this simple trick improves robustness and achieves results competitive to the state-of-the-art on the Stanford Question Answering Dataset (SQuAD), the Adversarial SQuAD, and the Microsoft MAchine Reading COmprehension Dataset (MS MARCO).
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("1712.03556")
get_code_for_paper("1712.03556")
have("1712.03556")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/1712.03556.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/1712.03556)
Connect an agent — have() is free.