• Computer Science
  • Published in ICLR 2016

Query-Reduction Networks for Question Answering

@inproceedings{Seo2016QueryReductionNF,
  title={Query-Reduction Networks for Question Answering},
  author={Minjoon Seo and Sewon Min and Ali Farhadi and Hannaneh Hajishirzi},
  booktitle={ICLR},
  year={2016}
}
Highlight Information
In this paper, we study the problem of question answering when reasoning over multiple facts is required. [...] Key Method QRN considers the context sentences as a sequence of state-changing triggers, and reduces the original query to a more informed query as it observes each trigger (context sentence) through time. Our experiments show that QRN produces the state-of-the-art results in bAbI QA and dialog tasks, and in a real goal-oriented dialog dataset. In addition, QRN formulation allows parallelization on…Expand Abstract

Citations

Publications citing this paper.
SHOWING 1-10 OF 69 CITATIONS

End-to-End Dynamic Query Memory Network for Entity-Value Independent Task-Oriented Dialog

VIEW 6 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

MEMO: A DEEP NETWORK FOR FLEXIBLE COMBINA-

VIEW 4 EXCERPTS
CITES BACKGROUND & RESULTS
HIGHLY INFLUENCED

MEMO: A Deep Network for Flexible Combination of Episodic Memories

VIEW 4 EXCERPTS
CITES BACKGROUND & RESULTS
HIGHLY INFLUENCED

Graph Convolutional Network with Sequential Attention for Goal-Oriented Dialogue Systems

VIEW 4 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

MEMO: A DEEP NETWORK FOR FLEXIBLE COMBINA-

  • EPISODIC MEMORIES
  • 2019
VIEW 4 EXCERPTS
CITES BACKGROUND & RESULTS
HIGHLY INFLUENCED

Hierarchical Pointer Memory Network for Task Oriented Dialogue

VIEW 4 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Scaffolding Networks: Incremental Learning and Teaching Through Questioning

VIEW 5 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

End-to-End Question Answering Models for Goal-Oriented Dialog Learning

VIEW 5 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2017
2020

CITATION STATISTICS

  • 21 Highly Influenced Citations

  • Averaged 22 Citations per year from 2017 through 2019

  • 50% Increase in citations per year in 2019 over 2018

References

Publications referenced by this paper.
SHOWING 1-10 OF 23 REFERENCES

Learning End-to-End Goal-Oriented Dialog

VIEW 8 EXCERPTS
HIGHLY INFLUENTIAL

Strongly-Typed Recurrent Neural Networks

VIEW 7 EXCERPTS
HIGHLY INFLUENTIAL

End-To-End Memory Networks

VIEW 13 EXCERPTS
HIGHLY INFLUENTIAL

Long Short-Term Memory

VIEW 9 EXCERPTS
HIGHLY INFLUENTIAL

Gated End-to-End Memory Networks

VIEW 6 EXCERPTS
HIGHLY INFLUENTIAL

Towards Neural Network-based Reasoning

VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

Adaptive Subgradient Methods for Online Learning and Stochastic Optimization

VIEW 2 EXCERPTS
HIGHLY INFLUENTIAL