Reader-Guided Passage Reranking for Open-Domain Question Answering

By Yuning Mao, Pengcheng He, Xiaodong Liu, Yelong Shen, Jianfeng Gao, Jiawei Han, Weizhu Chen. 2021

40 citations recorded by the source corpus.

Current open-domain question answering systems often follow a Retriever-Reader architecture, where the retriever first retrieves relevant passages and the reader then reads the retrieved passages to form an answer. In this paper, we propose a simple and effective passage reranking method, named Reader-guIDEd Reranker (RIDER), which does not involve training and reranks the retrieved passages solely based on the top predictions of the reader before reranking. We show that RIDER, despite its simplicity, achieves 10 to 20 absolute gains in top-1 retrieval accuracy and 1 to 4 Exact Match (EM) gains without refining the retriever or reader. In addition, RIDER, without any training, outperforms state-of-the-art transformer-based supervised rerankers. Remarkably, RIDER achieves 48.3 EM on the Natural Questions dataset and 66.4 EM on the TriviaQA dataset when only 1,024 tokens (7.8 passages on average) are used as the reader input after passage reranking.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Information Retrieval & Search, 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

1. Ji-rong Wen
2. Wayne Xin Zhao
3. Chenguang Zhu
4. Jing Liu
5. Ruiyang Ren
6. Xiang Ren
7. Haifeng Wang
8. Hua Wu

In Computer Vision and Pattern Recognition

1. Ji-rong Wen
2. Wayne Xin Zhao
3. Jing Liu
4. Ruiyang Ren
5. Chenguang Zhu
6. Haifeng Wang
7. Hua Wu
8. Yichong Xu

In Information Retrieval & Search

1. Xiang Ren
2. Martin Fajcik
3. Pavel Smrz
4. Haifeng Wang
5. Ji-rong Wen
6. Ruiyang Ren
7. Karel Ondrej
8. Yichong Xu

In Question Answering & Reading Comprehension

1. Xiang Ren
2. Ji-rong Wen
3. Wayne Xin Zhao
4. Chenguang Zhu

Citations in the corpus

• You Only Need One Model for Open-domain Question Answering (2021, neutral): “We also compare our pre-training to that of the additional data augmentation (Mao et al., 2021a; Ren et al., 2021; Oguz et al., 2021).”
• R2-D2: A Modular Baseline for Open-Domain Question Answering (2021, methodology): “Xin et al. (2020) achieved inference speedup using early exiting, Jang and Kim (2020) proposed a smaller and faster model, and Mao et al. (2021) came up with a method which uses reader’s predictions to rerank the passages.”
• KG-FiD: Infusing Knowledge Graph in Fusion-in-Decoder for Open-Domain Question Answering (2021, background): “…also proposed such as better training strategy (Qu et al., 2021), reranking based on retrieved passages (Wang et al., 2018; Nogueira and Cho, 2019; Mao et al., 2021), and knowledge distillation from reader to retriever (Izacard and Grave, 2020); (2) Improve the reader: changing from Recurrent…”
• RocketQAv2: A Joint Training Method for Dense Passage Retrieval and Passage Re-ranking (2021, background): “Such a two-stage procedure is particularly useful in a variety of natural language processing tasks, including question answering (Mao et al., 2021; Xiong et al., 2020b), dialogue system (Ji et al., 2014; Henderson et al., 2017) and entity linking (Gillick et al., 2019; Wu et al., 2020).”