Multi-step Retriever-Reader Interaction for Scalable Open-domain Question Answering
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.
NurtureToken New!

Token crowdsale for this paper ends in

Buy Nurture Tokens

Authors

Are you an author of this paper? Check the Twitter handle we have for you is correct.

Rajarshi Das (edit)
Shehzaad Dhuliawala (add twitter)
Manzil Zaheer (add twitter)
Andrew McCallum (edit)
Ask The Authors

Ask the authors of this paper a question or leave a comment.

Read it. Rate it.
#1. Which part of the paper did you read?

#2. The paper contains new data or analyses that is openly accessible?
#3. The conclusion is supported by the data and analyses?
#4. The conclusion is of scientific interest?
#5. The result is likely to lead to future research?

Github
Stargazers:
39
Forks:
3
Open Issues:
0
Network:
3
Subscribers:
2
Language:
Python
Youtube
Link:
None (add)
Views:
0
Likes:
0
Dislikes:
0
Favorites:
0
Comments:
0
Other
Sample Sizes (N=):
Inserted:
Words Total:
Words Unique:
Source:
Abstract:
None
05/14/19 06:01PM
8,145
2,437
Tweets
arxiv_cscl: Multi-step Retriever-Reader Interaction for Scalable Open-domain Question Answering https://t.co/Iltrx0geA3
arxiv_cs_LG: Multi-step Retriever-Reader Interaction for Scalable Open-domain Question Answering. Rajarshi Das, Shehzaad Dhuliawala, Manzil Zaheer, and Andrew McCallum https://t.co/J3J1kNXsRr
BrundageBot: Multi-step Retriever-Reader Interaction for Scalable Open-domain Question Answering. Rajarshi Das, Shehzaad Dhuliawala, Manzil Zaheer, and Andrew McCallum https://t.co/7REBsX0M3s
Images
Related