We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. We have no repository linked to it either. That is a statement about our graph, not about the paper.
Multi-hop reading comprehension focuses on one type of factoid question, where a system needs to properly integrate multiple pieces of evidence to correctly answer a question. Previous work approximates global evidence with local coreference information, encoding coreference chains with DAG-styled GRU layers within a gated-attention reader. However, coreference is limited in providing information for rich inference. We introduce a new method for better connecting global evidence, which forms more complex graphs compared to DAGs. To perform evidence integration on our graphs, we investigate two recent graph neural networks, namely graph convolutional network (GCN) and graph recurrent network (GRN). Experiments on two standard datasets show that richer global information leads to better answers. Our method performs better than all published results on these datasets.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("1809.02040")
get_code_for_paper("1809.02040")
have("1809.02040")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/1809.02040.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/1809.02040)
Connect an agent — have() is free.