Improving on Q & A Recurrent Neural Networks Using Noun-Tagging

07/12/2018
by   Erik Partridge, et al.
0

Often, more time is spent on finding a model that works well, rather than tuning the model and working directly with the dataset. Our research began as an attempt to improve upon a simple Recurrent Neural Network for answering "simple" first-order questions (QA-RNN), developed by Ferhan Ture and Oliver Jojic, from Comcast Labs, using the SimpleQuestions dataset. Their baseline model, a bidirectional, 2-layer LSTM RNN and a GRU RNN, have accuracies of 0.94 and 0.90, for entity detection and relation prediction, respectively. We fine tuned these models by doing substantial hyper-parameter tuning, getting resulting accuracies of 0.70 and 0.80, for entity detection and relation prediction, respectively. An accuracy of 0.984 was obtained on entity detection using a 1-layer LSTM, where preprocessing was done by removing all words not part of a noun chunk from the question. 100 relation prediction, but only 20 detection, which we believe to be much of the reason for our initial difficulties in replicating their result, despite the fact we were able to improve on their entity detection results.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/20/2017

Improved Neural Relation Detection for Knowledge Base Question Answering

Relation detection is a core component for many NLP applications includi...
research
12/05/2017

Strong Baselines for Simple Question Answering over Knowledge Graphs with and without Neural Networks

We examine the problem of question answering over knowledge graphs, focu...
research
04/21/2019

Estimating Forces of Robotic Pouring Using a LSTM RNN

In machine learning, it is very important for a robot to be able to esti...
research
01/05/2016

End-to-End Relation Extraction using LSTMs on Sequences and Tree Structures

We present a novel end-to-end neural model to extract entities and relat...
research
11/21/2022

3D Detection and Characterisation of ALMA Sources through Deep Learning

We present a Deep-Learning (DL) pipeline developed for the detection and...
research
03/23/2023

GETT-QA: Graph Embedding based T2T Transformer for Knowledge Graph Question Answering

In this work, we present an end-to-end Knowledge Graph Question Answerin...
research
09/01/2018

Finding the Answers with Definition Models

Inspired by a previous attempt to answer crossword questions using neura...

Please sign up or login with your details

Forgot password? Click here to reset