• DOI:10.1023/A:1022699029236
• Corpus ID: 189900099

Distributed Representations, Simple Recurrent Networks, And Grammatical Structure

@article{Elman2005DistributedRS,
  title={Distributed Representations, Simple Recurrent Networks, And Grammatical Structure},
  author={Jeffrey L. Elman},
  journal={Machine Learning},
  year={2005},
  volume={7},
  pages={195-225}
}

• J. Elman
• Published 1 September 1991
• Linguistics
• Machine Learning

In this paper three problems for a connectionist account of language are considered:1. What is the nature of linguistic representations?2. How can complex structural relationships such as constituent structure be represented?3. How can the apparently open-ended nature of language be accommodated by a fixed-resource system?Using a prediction task, a simple recurrent network (SRN) is trained on multiclausal sentences which contain multiply-embedded relative clauses. Principal component analysis of the hidden unit activation patterns reveals that the network solves the task by developing complex distributed representations which encode the relevant grammatical relations and hierarchical constituent structure. Differences between the SRN state representations and the more traditional pushdown store are discussed in the final section.