Learning speech semantics with keyword classification trees

IEEE International Conference on Acoustics Speech and Signal ProcessingPublished 1 January 1993

Roland Kühn, Renato De Mori

DOI10.1109/icassp.1993.319228

Citations12

TL;DR

A linguistic analyzer based on KCTs (keyword classification trees) was trained on sentences from the ATIS air travel task and incorporated into the system (CHANEL) built at CRIM for the Nov. 1992 ATIS benchmarks, and attained a reasonable performance level.

Abstract

A linguistic analyzer based on KCTs (keyword classification trees) was trained on sentences from the ATIS (Air Travel Information System) air travel task and incorporated into the system (CHANEL) built at CRIM (Centre de Recherche Informatique de Montreal) for the Nov. 1992 ATIS benchmarks. Word sequences were processed by a local parser that identified semantically important noun phrases and then passed through a forest of KCTs, each responsible for generating a different aspect of the semantic representation. CHANEL attained a reasonable performance level, despite its heavy reliance on KCTs rather than on handcoded linguistic rules. The CRIM speech recognition system had a recognition rate of 88.9% words correct; CHANEL is clearly robust.>

Keywords

Computer Science

BiometricsClassification and Regression Trees.

23,841 Citations1984Alexander Gordon, Leo Breiman +3 more

Evaluation of spoken language systems

397 Citations1990P. Price

This paper will address the emerging standards for evaluation of spoken language systems with quantifiable measures essential for comparing results and assessing claims.

IEEE Transactions on Pattern Analysis and Machine IntelligenceAn iterative growing and pruning algorithm for classification tree design

227 Citations1991S.B. Gelfand, C. Ravishankar +1 more

Robust parsing for spoken language systems

57 Citations1992Stephanie Seneff

A recent extension to the MIT ATIS (Air Travel Information Service) system, which allows it to answer a question when a full linguistic analysis fails, indicates that most of the recognizer errors are harmless in terms of meaning analysis, as long as a robust mechanism for accounting for the parsable phrases is in place.

Stochastic representation of conceptual structure in the ATIS task

53 Citations1991Roberto Pieraccini, Esther Levin +1 more

A model for a statistical representation of the conceptual structure in a restricted subset of spoken natural language used for segmenting a sentence into phrases and labeling them with concept relations (or cases) is proposed.

A template matcher for robust NL interpretation

51 Citations1991Eric Jackson, Douglas E. Appelt +3 more

The Template Matcher, a system built at SRI to provide robust natural-language interpretation in the Air Travel Information System (ATIS) domain, appears to be robust to both speech recognition errors and unanticipated or difficult locutions used by speakers.

Fragment processing in the DELPHI system

24 Citations1992David Stallard, Robert Bobrow

The complete fallback understanding component of BBN's DELPHI NL sysystem incorporates both syntax- and frame-based fragment combination sub-components, in an attempt to provide a smoother path from accurate but fragile conventional parsers on the one hand to the robust but less accurate schema-based methods on the other.

View PDF

Elsevier eBooksClassification Trees for Information Retrieval

19 Citations1991Stuart L. Crawford, Robert Fung +2 more

Experiments are described designed to assess the utility of a machine learning approach to the automatic construction of concept trees for information retrieval.

Speech understanding in open tasks

12 Citations1992Wayne Ward, Sunil Issar +7 more

This paper explains the techniques used in the system and the performance results on the standard set of tests used to evaluate systems.

View PDF