Incorporating Query Term Independence Assumption for Efficient Retrieval and Ranking using Deep Neural Networks

Classical information retrieval (IR) methods, such as query likelihood and BM25, score documents independently w.r.t. each query term, and then accumulate the scores. Assuming query term independence allows precomputing term-document scores using these modelswhich can be combined with specialized data structures, such as inverted index, for efficient retrieval. Deep neural IR models, in contrast, compare the whole query to the document and are, therefore, typically employed only for late stage re-ranking. We incorporate query term independence assumption into three state-of-the-art neural IR models: BERT, Duet, and CKNRMand evaluate their performance on a passage ranking task. Surprisingly, we observe no significant loss in result quality for Duet and CKNRMand a small degradation in the case of BERT. However, by operating on each query term independently, these otherwise computationally intensive models become amenable to offline precomputationdramatically reducing the cost of query evaluations employing state-of-the-art neural ranking models. This strategy makes it practical to use deep models for retrieval from large collectionsand not restrict their usage to late stage re-ranking.