SPARTA: Efficient Open-Domain Question Answering via Sparse Transformer Matching Retrieval
This addresses the efficiency and scalability challenges in open-domain question answering for users needing fast and interpretable retrieval systems, representing a novel method rather than an incremental improvement.
The paper tackled the problem of efficient neural retrieval for open-domain question answering by introducing SPARTA, a method that uses sparse representations instead of dense vectors, achieving state-of-the-art results on multiple tasks including open SQuAD and Natural Question.
We introduce SPARTA, a novel neural retrieval method that shows great promise in performance, generalization, and interpretability for open-domain question answering. Unlike many neural ranking methods that use dense vector nearest neighbor search, SPARTA learns a sparse representation that can be efficiently implemented as an Inverted Index. The resulting representation enables scalable neural retrieval that does not require expensive approximate vector search and leads to better performance than its dense counterpart. We validated our approaches on 4 open-domain question answering (OpenQA) tasks and 11 retrieval question answering (ReQA) tasks. SPARTA achieves new state-of-the-art results across a variety of open-domain question answering tasks in both English and Chinese datasets, including open SQuAD, Natuarl Question, CMRC and etc. Analysis also confirms that the proposed method creates human interpretable representation and allows flexible control over the trade-off between performance and efficiency.