Share your thoughts, 1 month free Claude Pro on usSee more
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
Information RetrievalBEIR
SciFact0.761
174
Document RankingTREC DL Track 2019 (test)
nDCG@1056.9
133
Passage retrievalMsMARCO (dev)
MRR@1021.5
116
RetrievalMS MARCO (dev)
MRR@100.215
84
Passage RankingMS MARCO (dev)
MRR@1037.5
75
Information RetrievalBRIGHT 1.0 (test)
nDCG@10 (Avg)13
41
Passage RankingTREC DL 2019 (test)
NDCG@1059
33
Long-horizon Question AnsweringLongMemEval-RR
F1 Score12.05
16
Tool RetrievalTOOLRET In-Domain (Avg)
nDCG@1051.5
15
Tool RetrievalTOOLRET Zero-Shot Code
nDCG@1025.4
15
Showing 10 of 19 rows

Other info

Code

Follow for update