Query-Reduction Networks for Question Answering

Minjoon Seo, Sewon Min, Ali Farhadi, Hannaneh Hajishirzi
6/14/2016
cs.CLcs.NE

Official code: seominjoon/qrn (138 stars, MIT, TensorFlow, last commit 2017-12-20).

Abstract

In this paper, we study the problem of question answering when reasoning over multiple facts is required. We propose Query-Reduction Network (QRN), a variant of Recurrent Neural Network (RNN) that effectively handles both short-term (local) and long-term (global) sequential dependencies to reason over multiple facts. 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 RNN's time axis, saving an order of magnitude in time complexity for training and inference.

View on arXivView PDF

Code Implementations(1)

seominjoon/qrnOfficial100%
TensorFlowMIT

Query-Reduction Networks (QRN)

13830HTML, ShellApr 17, 20168 years agoMIT
babidialogiclr2017qaqrn+3 more

Similar Papers

Towards Robust Temporal Reasoning of Large Language Models via a Multi-Hop QA Dataset and Pseudo-Instruction Tuning

85% match1 repo22023

TempoQR: Temporal Question Reasoning over Knowledge Graphs

84% match1 repo332021

Unlocking Temporal Question Answering for Large Language Models with Tailor-Made Reasoning Logic

83% match1 repo92023

Joint Multi-Facts Reasoning Network For Complex Temporal Question Answering Over Knowledge Graph

81% match2024

Time-aware Multiway Adaptive Fusion Network for Temporal Knowledge Graph Question Answering

80% match2023

Temporal-Aware Heterogeneous Graph Reasoning with Multi-View Fusion for Temporal Question Answering

80% match2026

Cite this paper

@article{seo2016queryreduction,
  title  = {Query-Reduction Networks for Question Answering},
  author = {Minjoon Seo and Sewon Min and Ali Farhadi and Hannaneh Hajishirzi},
  year   = {2016},
  eprint = {1606.04582},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1606.04582}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1606.04582.svg)](https://codeofpaper.com/paper/1606.04582)

Discussion