Relevance feedback strategies for recall-oriented neural information retrieval
This addresses the need for more reliable recall in critical applications like patent search and due diligence, offering an incremental improvement over existing active learning systems.
The paper tackles the problem of false negatives in recall-oriented information retrieval applications by proposing a relevance feedback method that iteratively re-ranks results using BERT-based dense-vector search and cumulative embedding sums, achieving a reduction in review effort of 17.85% to 59.04% compared to a no-feedback baseline.
In a number of information retrieval applications (e.g., patent search, literature review, due diligence, etc.), preventing false negatives is more important than preventing false positives. However, approaches designed to reduce review effort (like "technology assisted review") can create false negatives, since they are often based on active learning systems that exclude documents automatically based on user feedback. Therefore, this research proposes a more recall-oriented approach to reducing review effort. More specifically, through iteratively re-ranking the relevance rankings based on user feedback, which is also referred to as relevance feedback. In our proposed method, the relevance rankings are produced by a BERT-based dense-vector search and the relevance feedback is based on cumulatively summing the queried and selected embeddings. Our results show that this method can reduce review effort between 17.85% and 59.04%, compared to a baseline approach (of no feedback), given a fixed recall target