Elamur Research⌕
☰
home / papers / 1992 / TINA: A Natural Language System for Spoken Language Applications

TINA: A Natural Language System for Spoken Language Applications

Paper · 1992 · Stephanie Seneff

Summary

Spoken language systems need a natural language component that produces a meaning representation and also constrains the speech recognizer. To do the second job, a parser must reject ill-formed word strings rather than simply maximize coverage. Seneff presents TINA, a parser that combines context-free grammars, ATN-style networks and unification. Hand-written rewrite rules are compiled into a shared network for each left-hand category. Transition probabilities between sibling categories are then estimated automatically from training sentences, which are parsed through a bootstrapping procedure. Parsing runs top-down with a best-first stack-decoding queue. Features attached to categories, not rules, handle agreement, long-distance movement and semantic restrictions. Upper levels of the tree encode syntax and lower levels encode semantics, so a semantic frame can be read directly from the parse. The probabilistic network can predict next-word candidates. This lets TINA screen hypotheses from MIT's SUMMIT recognizer in two database-access domains. The work matters because it shows one grammar can support both understanding and recognition constraint, with long-distance constraints that go beyond bigram models.

Key points

  • TINA's unification constraints are tied to categories, and features pass between nodes by default. Hypotheses are copied nondestructively, so no explicit backtracking is needed.
  • Arc probabilities come from sibling-pair counts, normalized per left sibling, using special [start] and [end] nodes. In the appendix's three-digit number grammar, the transition from start to digits within hundreds-place gets probability 3/4.
  • In the same worked example, the test phrase "four fifteen" has a perplexity of roughly 14.
  • A built-in sentence generator exposes overgeneralization in the grammar and also produces a word-pair language model for the recognizer.
  • TINA is integrated with SUMMIT and filters either complete sentences or partial theories during the search. The work was funded by DARPA.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Institutions

🎓Massachusetts Institute of TechnologyCambridge · United States243 works · 76,506 citations

 Fields, topics and concepts

📚 Shelves 4The field of science this work belongs to (OpenAlex fields).Computer Science · 18,614 worksArtificial Intelligence · 17,965 worksArts and Humanities · 17,450 worksLanguage and Linguistics · 17,296 works

Cite

Cite as Stephanie Seneff. 1992. TINA: A Natural Language System for Spoken Language Applications. Computational Linguistics.

The paper itself, not this page. BibTeX from the library's record of the work.

@article{seneff1992tina,
  title = {{TINA: A Natural Language System for Spoken Language Applications}},
  author = {Stephanie Seneff},
  journal = {Computational Linguistics},
  year = {1992},
  url = {https://aclanthology.org/J92-1004/}
}

References

26 references, 1 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Boisen, S.; Chow, Y.-L.; Haas, A.; lngria, R.; Roukos, S.; and Stallard, D. (1989). "The BBN spoken language system." In Proceedings, DARPA Speech and Natural Language Workshop. 106-111. find
  2. Bresnan, J., ed. (1982). The Mental Representation of Grammatical Relations. Cambridge, MA: The MIT Press. find
  3. Chomsky, Noam (1977). "On wh-movement." In Formal Syntax, edited by P. Culicover, T. Wasow, and A. Akmajian. New York: Academic Press. find
  4. De Mattia, M., and Giachin, E. P. (1989). "Experimental results on large vocabulary continuous speech understanding." ICASSP-89 Proceedings. 691-694. find
  5. Fillmore, C. J. (1968). "The case for case." In Universals in Linguistic Theory, edited by E. Bach and R. Harms. New York: Holt, Rinehart, and Winston. 1-90. find
  6. Goodine, D.; Seneff, S.; Hirschman, L.; and Phillips, M. (1991). "Full integration of speech and language understanding in the MIT spoken language system." In Proceedings, 2nd European Conference on Speech Communication and Technology. Genova, Italy. 24-26. find
  7. Grishman, R.; Hirschman, L.; and Nhan, N. T. (1986). "Discovery procedures for sublanguage selectional patterns: Initial experiments." Computational Linguistics 12(3): 205-215.
  8. Hart, P.; Nilsson, N. J.; and Raphael B. (1968). "A formal basis for the heuristic determination of minimum cost paths." IEEE Transactions of Systems, Science and Cybernetics SSC-4(2): 100-107. find
  9. Hirschman, L.; Grishman, R.; and Sager, N. (1975). "Grammatically-based automatic word class formation." Information Processing and Management 11: 39-57. find
  10. Jelinek, E (1976). "Continuous speech recognition by statistical methods." IEEE Proceedings 64(4): 532-556. find
  11. Katz, S. M. (1987). "Estimation of probabilities from sparse data for the language model component of a speech recognizer." ASSP-35: 400-401. find
  12. Lamel, L.; Kassel, R. H.; and Seneff, S. (1986). "Speech database development: Design and analysis of the acoustic-phonetic corpus." In Proceedings, DARPA Speech Recognition Workshop. Palo Alto, CA. 100-109. find
  13. Lee, K. E (1989). Automatic Speech Recognition: The Development of the SPHINX System, Appendix I. Boston: Kluwer Academic Publishers. find
  14. Lee, K. F.; Hon, H. W.; and Reddy, R. (1989). "An overview of the SPHINX speech recognition system." IEEE Transactions on Acoustics, Speech, and Signal Processing 38(1): 35-46. find
  15. Niedermair, G. Th. (1989). "The use of a semantic network in speech dialogue." 1st European Conference on Speech Communication and Technology, Paris, France. 26-29. find
  16. Niemann, H. (1990). "The interaction of word recognition and linguistic processing in speech understanding." Invited Lecture, NATO-ASI Workshop on Speech Recognition and Understanding, Cetraro, Italy. find
  17. Pallett, D. (1989). "Benchmark tests for DARPA resource management database performance evaluations." In Proceedings, ICASSP-89. 536-539. find
  18. Seneff, S.; Glass, J.; Goddeau, D.; Goodine, D.; Hirschman, L.; Leung, H.; Phillips, M.; Polifroni, J.; and Zue, V. (1991). "Development and preliminary evaluation of the MIT ATIS system." Fourth DARPA Speech and Natural Language Workshop, Asilomar, CA. 88-93. find
  19. Viterbi, A. (1967). "Error bounds for convolutional codes and an asymptotically optimal decoding algorithm." IEEE Transactions on Information Theory IT-13. 260-269. find
  20. Woods, W. A. (1970). "Transition network grammars for natural language analysis." Commun. of the ACM 13: 591-606. find
  21. Woods, W. A. (1986). "Semantics and quantification in natural language question answering." In Readings in Natural Language Processing, edited by B. J. Grosz, K. S. Jones; and B. L. Webber. Los Altos, CA: Morgan Kaufmann. 205-248. find
  22. Young, S. R. (1989). "The minds system: Using context and dialog to enhance speech recognition." Proceedings, DARPA Speech and Natural Language Workshop. 131-136. find
  23. Zue, V.; Daly, N.; Glass, J.; Goodine, D.; Leung, H.; Phillips, M.; Polifroni, J.; Seneff, S.; and Sodof, M. (1989a). "The collection and preliminary analysis of a spontaneous speech database." DARPA Speech and Natural Language Workshop. Harwichport, MA. 15-18. find
  24. Zue, V.; Glass, J.; Phillips, M.; and Seneff, S. (1989b). "The MIT SUMMIT speech recognition system, a progress report." Proceedings, DARPA Speech and Natural Language Workshop. Philadelphia. 21-23. find
  25. Zue, V.; Glass, J.; Goodine, D.; Leung, H.; Phillips;, M.; Polifroni, J.; and Seneff, S. (1990). "The VOYAGER speech understanding system: Preliminary development and evaluation." IEEE International Conference on Acoustics, Speech and Signal Processing. Albuquerque, NM. 73-76. find
  26. Zue, V.; Glass, J.; Goodine, D.; Leung, H.; Phillips, M.; Polifroni, J.; and Seneff, S. (1991). "Integration of speech recognition and natural language processing in the MIT VOYAGER system." IEEE International Conference on Acoustics, Speech and Signal Processing. Toronto, Ontario. 14-17. find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/seneff-1992-tina-natural-language-system-spoken/