Reproduce “Effective and Efficient Query-aware Snippet Extraction for Web Search” on OpenResearch

Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.

Universal app for Apple silicon and Intel. Requires macOS 11 or later.

About this paper

Jingwei Yi, Fangzhao Wu, Chuhan Wu, Xiaolong Huang, Binxing Jiao, Guangzhong Sun, Xing Xie

The authors introduce Efficient-DeepQSE, a system for selecting query-relevant search snippets from webpages. It caches sentence representations, narrows candidates, then applies detailed query-aware scoring while modeling page context. On the English test set, it reports precision at one of 77.03±0.27%, above PARADE’s 73.19±0.16%; its multilingual score remains below full DeepQSE’s.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.