AI King - Japan's No.1 Quiz AI Competition and won 3rd place|PKSHA Delta 2023-01-04
Talk about combining searches.
BM25: Lexical Match Base
Dense Passage Retriever (DPR)... Dense vector-based using pre-trained models
Very small overlap in search results for both DPR and BM25
→ good points on both sides.
All teams are Retriever-Reader type
Surveying papers around information retrieval, we found several studies in this context, and seq-to-seq based ones are more accurate than building classifiers on BERT basis
This page is auto-translated from /nishio/検索を組み合わせる using DeepL. If you looks something interesting but the auto-translated English is not good enough to understand it, feel free to let me know at @nishio_en. I'm very happy to spread my thought to non-Japanese readers.