Retrieve, Read, Rerank: Towards End-to-End Multi-Document Reading Comprehension

By Minghao Hu, Yuxing Peng, Zhen Huang, Dongsheng Li. 2019

68 citations recorded by the source corpus.

This paper considers the reading comprehension task in which multiple documents are given as input. Prior work has shown that a pipeline of retriever, reader, and reranker can improve the overall performance. However, the pipeline system is inefficient since the input is re-encoded within each module, and is unable to leverage upstream components to help downstream training. In this work, we present RE^3QA, a unified question answering model that combines context retrieving, reading comprehension, and answer reranking to predict the final answer. Unlike previous pipelined approaches, RE^3QA shares contextualized text representation across different components, and is carefully designed to use high-quality upstream outputs (e.g., retrieved context or candidate answers) for directly supervising downstream modules (e.g., the reader or the reranker). As a result, the whole network can be trained end-to-end to avoid the context inconsistency problem. Experiments show that our model outperforms the pipelined baseline and achieves state-of-the-art results on two versions of TriviaQA and two variants of SQuAD.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Natural Language Processing, Question Answering & Reading Comprehension

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 Computer Vision and Pattern Recognition

In Natural Language Processing

In Question Answering & Reading Comprehension

Citations in the corpus

Learning to Retrieve Reasoning Paths over Wikipedia Graph for Question Answering (2019, background): “It is known to be effective in open-domain QA to use distantly supervised examples, which are not originally associated with the questions but include expected answer strings (Chen et al., 2017; Wang et al., 2018a; Hu et al., 2019).”
A Multi-Type Multi-Span Network for Reading Comprehension that Requires Discrete Reasoning (2019, neutral): “Morevoer, answer reranking has been well studied in several prior works (Cui et al., 2016; Wang et al., 2018a,b,c; Hu et al., 2019).”
Pre-training Tasks for Embedding-based Large-scale Retrieval (2020, background): “In open-domain question answering, q represents a question and d represents an evidence passage containing the answer (Chen et al., 2017; Hu et al., 2019; Lee et al., 2019).”
SPARTA: Efficient Open-Domain Question Answering via Sparse Transformer Matching Retrieval (2020, unknown): “…et al., 2018) - 30.2 MINIMAL (Min et al., 2018) 42.5 32.7 DenSPI-hybrid (Seo et al., 2019) 44.4 36.2 BERTserini (Yang et al., 2019a) 46.1 38.6 RE 3 (Hu et al., 2019) 50.2 41.9 Multi-passage (Wang et al., 2019) 60.9 53.0 Graph-retriever (Asai et al., 2019) (Min et al., 2019) 28.8 28.1 ORQA(Lee et…”
Retrieve, Rerank, Read, then Iterate: Answering Open-Domain Questions of Arbitrary Complexity from Text (2020, background): “Aside from the reading comprehension and retrieval components, researchers have also found reranking search results (Wang et al., 2018a) or answer candidates (Wang et al., 2018b; Hu et al., 2019).”