Implicity Defined Neural Networks for Sequence Labeling

Abstract

In this work, we propose a novel, implicitly defined neural network architecture and describe a method to compute its components. The proposed architecture forgoes the causality assumption previously used to formulate recurrent neural networks and allow the hidden states of the network to coupled together, allowing potential improvement on problems with complex, long-distance dependencies. Initial experiments demonstrate the new architecture outperforms both the Stanford Parser and a baseline bidirectional network on the Penn Treebank Part-of-Speech tagging task and a baseline bidirectional network on an additional artificial random biased walk task.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Feb 13, 2017
Accession Number
AD1028510

Entities

People

  • Brian J. Thompson
  • Michaeel M. Kazi

Organizations

  • Massachusetts Institute of Technology

Tags

DTIC Thesaurus Topics

  • Air Force
  • Artificial Intelligence Software
  • Automated Speech Recognition
  • Boundary Value Problems
  • Computational Linguistics
  • Computational Science
  • Differential Equations
  • Equations
  • Language
  • Linguistics
  • Machine Translation
  • Markov Models
  • Natural Language Processing
  • Neural Networks
  • Random Walk
  • Recurrent Neural Networks
  • Signal Processing

Fields of Study

  • Computer science

Readers

  • Computational Linguistics
  • Neural Network Machine Learning.

Technology Areas

  • AI & ML
  • AI & ML - Machine Learning Algorithms
  • AI & ML - Machine Translation
  • AI & ML - Neural Networks