Prediction and Semantic Association

Abstract

We explore the consequences of viewing semantic association as the result of attempting to predict the concepts likely to arise in a particular context. We argue that the success of existing accounts of semantic representation comes as a result of indirectly addressing this problem, and show that a closer correspondence to human data can be obtained by taking a probabilistic approach that explicitly models the generative structure of language.

Cite

Text

Griffiths and Steyvers. "Prediction and Semantic Association." Neural Information Processing Systems, 2002.

Markdown

[Griffiths and Steyvers. "Prediction and Semantic Association." Neural Information Processing Systems, 2002.](https://mlanthology.org/neurips/2002/griffiths2002neurips-prediction/)

BibTeX

@inproceedings{griffiths2002neurips-prediction,
  title     = {{Prediction and Semantic Association}},
  author    = {Griffiths, Thomas L. and Steyvers, Mark},
  booktitle = {Neural Information Processing Systems},
  year      = {2002},
  pages     = {11-18},
  url       = {https://mlanthology.org/neurips/2002/griffiths2002neurips-prediction/}
}