• Skip to primary navigation
  • Skip to main content
SRI logo
  • About
    • Press room
    • Our history
  • Expertise
    • Advanced imaging systems
    • Artificial intelligence
    • Biomedical R&D services
    • Biomedical sciences
    • Computer vision
    • Cyber & formal methods
    • Education and learning
    • Innovation strategy and policy
    • National security
    • Ocean & space
    • Quantum
    • QED-C
    • Robotics, sensors & devices
    • Speech & natural language
    • Video test & measurement
  • Ventures
  • NSIC
  • Careers
  • Contact
  • 日本支社
Search
Close
Artificial intelligence publications April 1, 2015

Neural network joint modeling via context-dependent projection

Citation

Copy to clipboard


Y-C. Tam and Y. Lei, “Neural network joint modeling via context-dependent projection,” In Proc. 40th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2015.

Abstract

Neural network joint modeling (NNJM) has produced huge improvement in machine translation performance.  As in standard neural network language modeling, a context-independent linear projection is applied to project a sparse input vector into a continuous representation at each word position.  Because neighboring words are dependent on each other, context-independent projection may not be optimal.  We propose a context-dependent linear projection approach which considers neighboring words.  Experimental results showed that the proposed approach further improves NNJM by 0.5 BLEU for English-Iraqi Arabic translation in N-best rescoring. Compared to a baseline using hierarchical phrases and sparse features, NNJM with our proposed approach has achieved a 2 BLEU improvement.

↓ Download

Share this

How can we help?

Once you hit send…

We’ll match your inquiry to the person who can best help you.

Expect a response within 48 hours.

Career call to action image

Make your own mark.

Search jobs

Our work

Case studies

Publications

Timeline of innovation

Areas of expertise

Institute

Leadership

Press room

Media inquiries

Compliance

Careers

Job listings

Contact

SRI Ventures

Our locations

Headquarters

333 Ravenswood Ave
Menlo Park, CA 94025 USA

+1 (650) 859-2000

Subscribe to our newsletter


日本支社
SRI International
  • Contact us
  • Privacy Policy
  • Cookies
  • DMCA
  • Copyright © 2022 SRI International