Early Syntactic Bootstrapping in an Incremental Memory-Limited Word Learner

2018

Conference: proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence (AAAI-18)

Sepideh Sadeghi and Matthias Scheutz

We first present a probabilistic framework in which the knowledge of word order and word referent can be jointly learned in the absence of any prior syntactic knowledge (e.g., “subjecthood” or lexical categories), then we use our framework to study the utility of joint acquisition of word order and word referent and its onset, in improving the word learning results.

@inproceedings{sadeghi2018aaai,
  title={Early Syntactic Bootstrapping in an Incremental Memory-Limited Word Learner},
  author={Sepideh Sadeghi and Matthias Scheutz},
  year={2018},
  booktitle={proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence (AAAI-18)},
  url={https://hrilab.tufts.edu/publications/sadeghi2018aaai.pdf}
}