SPARTA: Efficient Open-Domain Question Answering via Sparse Transformer Matching Retrieval
arXiv:2009.13013
Abstract
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.
11 pages
References in corpus (18)
- Adam: A Method for Stochastic Optimization
- A Deep Relevance Matching Model for Ad-hoc Retrieval
- SQuAD: 100,000+ Questions for Machine Comprehension of Text
- End-to-End Neural Ad-hoc Ranking with Kernel Pooling
- End-to-End Open-Domain Question Answering with BERTserini
- Poly-encoders: Transformer Architectures and Pre-training Strategies for Fast and Accurate Multi-sentence Scoring
- Learning to Retrieve Reasoning Paths over Wikipedia Graph for Question Answering
- HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering
- RACE: Large-scale ReAding Comprehension Dataset From Examinations
- Pre-training Tasks for Embedding-based Large-scale Retrieval
- DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs
- DRCD: a Chinese Machine Reading Comprehension Dataset
- Efficient and Robust Question Answering from Minimal Context over Documents
- Multi-passage BERT: A Globally Normalized BERT Model for Open-domain Question Answering
- MRQA 2019 Shared Task: Evaluating Generalization in Reading Comprehension
- A Discrete Hard EM Approach for Weakly Supervised Question Answering
- Ranking Paragraphs for Improving Answer Recall in Open-Domain Question Answering
- Retrieve, Read, Rerank: Towards End-to-End Multi-Document Reading Comprehension