Multi-step Retriever-Reader Interaction for Scalable Open-domain Question Answering

By Rajarshi Das, Shehzaad Dhuliawala, Manzil Zaheer, Andrew McCallum. 2019

173 citations recorded by the source corpus.

This paper introduces a new framework for open-domain question answering in which the retriever and the reader iteratively interact with each other. The framework is agnostic to the architecture of the machine reading model, only requiring access to the token-level hidden representations of the reader. The retriever uses fast nearest neighbor search to scale to corpora containing millions of paragraphs. A gated recurrent unit updates the query at each step conditioned on the state of the reader and the reformulated query is used to re-rank the paragraphs by the retriever. We conduct analysis and show that iterative interaction helps in retrieving informative paragraphs from the corpus. Finally, we show that our multi-step-reasoning framework brings consistent improvement when applied to two widely used reader architectures DrQA and BiDAF on various large open-domain datasets --- TriviaQA-unfiltered, QuasarT, SearchQA, and SQuAD-Open.

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

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. Mohit Bansal
  2. Jianfeng Gao
  3. Luke S. Zettlemoyer
  4. Percy Liang
  5. Hannaneh Hajishirzi
  6. Caiming Xiong
  7. Graham Neubig
  8. Yejin Choi

In Computer Vision and Pattern Recognition

  1. Luc Van Gool
  2. Jianfeng Gao
  3. Dacheng Tao
  4. Mohit Bansal
  5. Trevor Darrell
  6. Hannaneh Hajishirzi
  7. Xiaogang Wang
  8. Andrew Zisserman

In Retrieval-Augmented Generation

  1. Hannaneh Hajishirzi
  2. Sebastian Riedel
  3. Danqi Chen
  4. Wen-tau Yih
  5. Akari Asai
  6. Matei A. Zaharia
  7. Christopher Potts
  8. Omar Khattab

In Information Retrieval & Search

  1. Wen-tau Yih
  2. Hannaneh Hajishirzi
  3. Sebastian Riedel
  4. Danqi Chen
  5. Jinhyuk Lee
  6. Patrick Lewis
  7. Jimmy J. Lin
  8. Akari Asai

Citations in the corpus