The Integration of Unification-Based Syntax/Semantics and Memory-Based Pragmatics for Real-Time Understanding of Noisy Continuous Speech Input

Abstract

Real-time understanding of speech input is difficult especially because the input is often noisy and elliptic. Multiple morphophonemic and lexical hypotheses generated for a single input sentence cannot be resolved by local semantics alone. We have developed a system in which unification-based parsing of speech input is integrated with thematic memory-based spreading activation that supplies extra-sentential knowledge that can help to disambiguate noisy and elliptic real-time speaker-independent continuous speech input.

Cite

Text

Tomabechi and Tomita. "The Integration of Unification-Based Syntax/Semantics and Memory-Based Pragmatics for Real-Time Understanding of Noisy Continuous Speech Input." AAAI Conference on Artificial Intelligence, 1988.

Markdown

[Tomabechi and Tomita. "The Integration of Unification-Based Syntax/Semantics and Memory-Based Pragmatics for Real-Time Understanding of Noisy Continuous Speech Input." AAAI Conference on Artificial Intelligence, 1988.](https://mlanthology.org/aaai/1988/tomabechi1988aaai-integration/)

BibTeX

@inproceedings{tomabechi1988aaai-integration,
  title     = {{The Integration of Unification-Based Syntax/Semantics and Memory-Based Pragmatics for Real-Time Understanding of Noisy Continuous Speech Input}},
  author    = {Tomabechi, Hideto and Tomita, Masaru},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {1988},
  pages     = {724-728},
  url       = {https://mlanthology.org/aaai/1988/tomabechi1988aaai-integration/}
}