Abstract
Language models have broad adoption in predictive typing tasks. When the typing history contains numerous errors, as in open-vocabulary predictive typing with brain-computer interface (BCI) systems, we observe significant performance degradation in both n-gram and recurrent neural network language models trained on clean text. In evaluations of ranking character predictions, training recurrent LMs on noisy text makes them much more robust to noisy histories, even when the error model is misspecified. We also propose an effective strategy for combining evidence from multiple ambiguous histories of BCI electroencephalogram measurements.- Anthology ID:
- W19-1707
- Volume:
- Proceedings of the Eighth Workshop on Speech and Language Processing for Assistive Technologies
- Month:
- June
- Year:
- 2019
- Address:
- Minneapolis, Minnesota
- Venue:
- SLPAT
- SIG:
- SIGSLPAT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 44–51
- Language:
- URL:
- https://aclanthology.org/W19-1707
- DOI:
- 10.18653/v1/W19-1707
- Cite (ACL):
- Rui Dong, David Smith, Shiran Dudy, and Steven Bedrick. 2019. Noisy Neural Language Modeling for Typing Prediction in BCI Communication. In Proceedings of the Eighth Workshop on Speech and Language Processing for Assistive Technologies, pages 44–51, Minneapolis, Minnesota. Association for Computational Linguistics.
- Cite (Informal):
- Noisy Neural Language Modeling for Typing Prediction in BCI Communication (Dong et al., SLPAT 2019)
- PDF:
- https://preview.aclanthology.org/remove-xml-comments/W19-1707.pdf