Dong Yu, Dian Yu, Jianshu Chen, Xiaoman Pan, Xiang Yue, Wenlin Yao
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 consider the problem of pretraining a twostage open-domain question answering (QA) system (retriever + reader) with strong transfer capabilities. The key challenge is how to construct a large amount of high-quality question-answer-context triplets without taskspecific annotations. Specifically, the triplets should align well with downstream tasks by: (i) covering a wide range of domains (for opendomain applications), (ii) linking a question to its semantically relevant context with supporting evidence (for training the retriever), and (iii) identifying the correct answer in the context (for training the reader). Previous pretraining approaches generally fall short of one or more of these requirements. In this work, we automatically construct a large-scale corpus that meets all three criteria by consulting millions of references cited within Wikipedia. The well-aligned pretraining signals benefit both the retriever and the reader significantly. Our pretrained retriever leads to 2%-10% absolute gains in top-20 accuracy. And with our pretrained reader, the entire system improves by up to 4% in exact match. 1
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2203.08928")
get_code_for_paper("2203.08928")
have("2203.08928")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2203.08928.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2203.08928)
Connect an agent — have() is free.