ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 1412.6650
60
15
v1v2v3v4 (latest)

Incremental Adaptation Strategies for Neural Network Language Models

20 December 2014
Aram Ter-Sarkisov
Holger Schwenk
Loïc Barrault
Fethi Bougares
ArXiv (abs)PDFHTML
Abstract

It is today acknowledged that neural network language models outperform back- off language models in applications like speech recognition or statistical machine translation. However, training these models on large amounts of data can take several days. We present efficient techniques to adapt a neural network language model to new data. Instead of training a completely new model or rely on mixture approaches, we propose two new methods: continued training on resampled data or insertion of adaptation layers. We present experimental results in an CAT en- vironment where the post-edits of professional translators are used to improve an SMT system. Both methods are very fast and achieve significant improvements without over-fitting the small adaptation data.

View on arXiv
Comments on this paper