arxivst stuff from arxiv that you should probably bookmark

Improving Context Aware Language Models

Abstract · Apr 21, 2017 02:27 ·

adapting layer embedding variables zweig rnnlm adapt context hashing cs-cl

Arxiv Abstract

  • Aaron Jaech
  • Mari Ostendorf

Increased adaptability of RNN language models leads to improved predictions that benefit many applications. However, current methods do not take full advantage of the RNN structure. We show that the most widely-used approach to adaptation (concatenating the context with the word embedding at the input to the recurrent layer) is outperformed by a model that has some low-cost improvements: adaptation of both the hidden and output layers. and a feature hashing bias term to capture context idiosyncrasies. Experiments on language modeling and classification tasks using three different corpora demonstrate the advantages of the proposed techniques.

Read the paper (pdf) »