Syntactic and semantic features for human like judgement in spoken CALL

Ahmed Magooda, Diane Litman


Educational applications of Natural Language Processing (NLP) and Automatic Speech Recognition (ASR) have included providing learners with helpful and accurate feedback. In this paper we present a system that takes a first step towards providing feedback during spoken Computer-Assisted Language Learning (spokenCALL). We propose a machine learning based approach that combines syntactic and semantic features in order to accept or reject a textual response given a provided prompt. Our approach was evaluated as part of the SpokenCALL shared task, ranking third place among the submitted systems and outperforming the provided baselines.


 DOI: 10.21437/SLaTE.2017-19

Cite as: Magooda, A., Litman, D. (2017) Syntactic and semantic features for human like judgement in spoken CALL. Proc. 7th ISCA Workshop on Speech and Language Technology in Education, 109-114, DOI: 10.21437/SLaTE.2017-19.


@inproceedings{Magooda2017,
  author={Ahmed Magooda and Diane Litman},
  title={Syntactic and semantic features for human like judgement in spoken CALL},
  year=2017,
  booktitle={Proc. 7th ISCA Workshop on Speech and Language Technology in Education},
  pages={109--114},
  doi={10.21437/SLaTE.2017-19},
  url={http://dx.doi.org/10.21437/SLaTE.2017-19}
}