Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Document Expansion by Query Prediction

About

One technique to improve the retrieval effectiveness of a search engine is to expand documents with terms that are related or representative of the documents' content.From the perspective of a question answering system, this might comprise questions the document can potentially answer. Following this observation, we propose a simple method that predicts which queries will be issued for a given document and then expands it with those predictions with a vanilla sequence-to-sequence model, trained using datasets consisting of pairs of query and relevant documents. By combining our method with a highly-effective re-ranking component, we achieve the state of the art in two retrieval tasks. In a latency-critical regime, retrieval results alone (without re-ranking) approach the effectiveness of more computationally expensive neural re-rankers but are much faster.

Rodrigo Nogueira, Wei Yang, Jimmy Lin, Kyunghyun Cho• 2019

Related benchmarks

TaskDatasetResultRank
Passage retrievalMsMARCO (dev)
MRR@1021.5
116
Document RankingTREC DL Track 2019 (test)
nDCG@1056.9
96
RetrievalMS MARCO (dev)
MRR@100.215
84
Passage RankingMS MARCO (dev)
MRR@1037.5
73
Passage RankingTREC DL 2019 (test)
NDCG@1059
33
Tool RetrievalTOOLRET In-Domain (Avg)
nDCG@1051.5
15
Tool RetrievalTOOLRET Zero-Shot Code
nDCG@1025.4
15
Tool RetrievalTOOLRET Zero-Shot Web*
nDCG@1026.6
15
Tool RetrievalTOOLRET Zero-Shot Macro-Avg
nDCG@1028.4
15
Tool RetrievalTOOLRET Zero-Shot Custom
nDCG@1033.3
15
Showing 10 of 14 rows

Other info

Code

Follow for update