SPARTA: Efficient Open-Domain Question Answering via Sparse Transformer Matching Retrieval

By Tiancheng Zhao, Xiaopeng Lu, Kyusong Lee. 2020

110 citations recorded by the source corpus.

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, 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.

Subfields: Artificial Intelligence, Information Retrieval & Search, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Information Retrieval & Search

In Natural Language Processing

Citations in the corpus

Autoregressive Search Engines: Generating Substrings as Document Identifiers (2022, background): “…on term-weighting schemes, with many recent works proposing sophisticated, contextualized weights for both queries, and documents(Dai and Callan, 2019; Gao et al., 2021; Lin and Ma, 2021; Mallia et al., 2021; Dai and Callan, 2020; Bai et al., 2020; Zhao et al., 2021; Formal et al., 2021b,a).”
Adaptive Information Seeking for Open-Domain Question Answering (2021, neutral): “…- 100 Multi-step Reasoner (Das et al., 2019a) 31.9 39.2 5 MUPPET (Feldman and El-Yaniv, 2019) 39.3 46.2 45 GRR † (Asai et al., 2020) 56.5 63.8 ≥ 500 SPARTA † (Zhao et al., 2021) 59.3 66.5 - IRRR † (Qi et al., 2020) 56.8 63.2 ≥ 150 AISO large 59.5 67.6 24.8 Table 3: Question answering performance…”
SPLADE v2: Sparse Lexical and Expansion Model for Information Retrieval (2021, methodology): “However, EPIC and SPARTA (document) representations are not sparse enough by construction – unless resorting on top-𝑘 pooling – contrary to SparTerm, for which fast retrieval is thus possible.”
SPLADE: Sparse Lexical and Expansion Model for First Stage Ranking (2021, methodology): “A second solution to this problem, that has been chosen by recent works such as [1, 16, 29], is to estimate the importance of each term of the vocabulary implied by each term of the document, i.”
BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models (2021, background): “DeepCT and SPARTA both use a transformer network to learn term weighting.”
Retrieving and Reading: A Comprehensive Survey on Open-domain Question Answering (2021, methodology): “As another example, SPARTA [81] develops a neural ranker to calculate the token-level matching score using dot product between a non-contextualized encoded (e.g., BERT word embedding) question and a contextualized encoded (e.g., BERT encoder) document.”
A Systematic Multi-Domain Evaluation of Document Retrievers (2026, unknown): “Retrievers. docT5query [58] expands documents by generating multiple queries for each and retrieving with BM25. query2doc [80] instead expands the query, generating a pseudo-document and again retrieving with BM25, while HyDE [19] generates a hypothetical document and retrieves with the Contriever.”
Granite Embedding Multilingual R2 Models (2026, unknown): “…commonly used in retrieval, where document relevance to a query is scored by embedding similarity (Dunn et al., 2017; Xiong et al., 2020; Neelakantan et al., 2022; Zamani et al., 2018; Zhao et al., 2020), as well as in document clustering (An-gelov, 2020) and text classification (Sun et al., 2019).”
Granite Embedding R2 Models (2025, unknown): “…the relevance of a document to a given query can be determined by the similarity of their embeddings (Dunn et al., 2017; Xiong et al., 2020; Neelakantan et al., 2022; Zamani et al., 2018; Zhao et al., 2020), but also in document clustering (Angelov, 2020) and text classification (Sun et al., 2019).”
Granite Embedding Models (2025, unknown): “…the relevance of a document to a given query can be determined by the similarity of their embeddings (Dunn et al., 2017; Xiong et al., 2020; Neelakantan et al., 2022)(Zamani et al., 2018; Zhao et al., 2020), but also in document clustering (Angelov, 2020) and text classification (Sun et al., 2019).”