Rapid development of spoken language understanding grammars

Deliverable D, 2005

1993

We are developing a spoken dialogue system that accepts speaker-independent continuous utterances and responds to them. Two approaches are adopted and compared. Syntax-driven approach first applies syntactic analysis to constrain the input and passes syntactically accepted sentence candidates to semantic analysis. Keyword-driven approach performs keyword spotting and generates a lattice of keyword candidates as the input to semantic analyzer. For syntactic analysis, we realize LR parsing based on A* search, using word-pair constraint as heuristics. For keyword spotting, heuristic language model is incorporated to constrain the input containing the keywords. Semantic analyzer is based on a semantic network and a semantic representation is constructed by traversing the paths of the network nodes that are activated as the corresponding words are recognized. Experimental results shows that syntax-driven approach is superior to keyword-driven approach that is expected to be robust.

2002

To facilitate the development of speech enabled applications and services, researchers have been working on a variety of smart tools. Recently we have introduced a schema-based context free grammar learning algorithm aiming at the development of real applications. In that paper we have described the algorithm and given some experimental results on the data of our in-house project. To study the general applicability of the algorithm as well as to provide the research community with more informative results, we have applied the algorithm to the well studied ATIS task and compared the performance of the learned grammar with one of the best performers in ATIS evaluations. The results show that the semi-automatically learned grammar achieves comparable performance to the manually authored grammar.

音声科学研究 Studia Phonologica, 1993

We are developing a spoken dialogue system that accepts speaker-independent continuous utterances and responds to them. Two approaches are adopted and compared. Syntax-driven approach first applies syntactic analysis to constrain the input and passes syntactically accepted sentence candidates to semantic analysis. Keyword-driven approach performs keyword spotting and generates a lattice of keyword candidates as the input to semantic analyzer. For syntactic analysis, we realize LR parsing based on A* search, using word-pair constraint as heuristics. For keyword spotting, heuristic language model is incorporated to constrain the input containing the keywords. Semantic analyzer is based on a semantic network and a semantic representation is constructed by traversing the paths of the network nodes that are activated as the corresponding words are recognized. Experimental results shows that syntax-driven approach is superior to keyword-driven approach that is expected to be robust.

Dialogue Systems are now more and more used in real life. However, such systems are usually difficult for lay people to create. Some less complicated methods have been proposed, although with less powerful understanding capability. After introducing and comparing the approaches mentioned above, the grammar parsing part, named GrammarTool, of a natural language text interface Spoken Dialogue System (SDS) toolkit, named SDS Lite, is described in detail. Our system deals with Chinese dialogue and makes it very easy for lay people to learn and create their own SDS.

2001 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.01CH37221), 2001

When dialogue system developers tackle a new domain, much ef- fort is required; the development of different parts of the system usually proceeds independently. Yet it may be profitable to coor- dinate development efforts between different modules. Here, we focus our efforts on extending small amounts of language model training data by integrating semantic classes that were created for a natural language understanding module. By converting finite state parses of a training corpus into a probabilistic context free grammar and subsequently generating artificial data from the con- text free grammar, we can significantly reduce perplexity and ASR word error for situations with little training data. Experiments are presented using data from the ATIS and DARPA Communicator travel corpora.

2006

This book provides a detailed overview of Regulus, an open-source toolkit for building and compiling grammars for spoken dialog systems, which has been used for a number of applications including Clarissa, a spoken language system in use on the International Space Station. The focus is on controlled-language user-initiative systems, in which the user drives the dialog, but is required to use constrained language. Such a spoken language interface allows for a constrained range of commands-for example, "open the pod-bay doors"-to be issued in circumstances where, ergonomically, other interface options are infeasible. The emphasis of the approach, given the kind of application that is the focus of the work, is thus less on robustness of speech recognition and more on depth of semantic processing and quality of the dialog management. It is an interesting book, one which succeeds in motivating key problems and presenting general approaches to solving them, with enough in the way of explicit details to allow even a complete novice in spoken language processing to implement simple dialog systems.

IEEE Transactions on Audio, Speech and Language Processing, 2000

Spoken language understanding (SLU) aims at extracting meaning from natural language speech. Over the past decade, a variety of practical goal-oriented spoken dialog systems have been built for limited domains. SLU in these systems ranges from understanding predetermined phrases through fixed grammars, extracting some predefined named entities, extracting users' intents for call classification, to combinations of users' intents and named entities. In this paper, we present the SLU system of VoiceTone ® (a service provided by AT&T where AT&T develops, deploys and hosts spoken dialog applications for enterprise customers). The SLU system includes extracting both intents and the named entities from the users' utterances. For intent determination, we use statistical classifiers trained from labeled data, and for named entity extraction we use rule-based fixed grammars. The focus of our work is to exploit data and to use machine learning techniques to create scalable SLU systems which can be quickly deployed for new domains with minimal human intervention. These objectives are achieved by 1) using the predicate-argument representation of semantic content of an utterance; 2) extending statistical classifiers to seamlessly integrate hand crafted classification rules with the rules learned from data; and 3) developing an active learning framework to minimize the human labeling effort for quickly building the classifier models and adapting them to changes. We present an evaluation of this system using two deployed applications of VoiceTone ® .

IEEE Signal Processing Magazine, 2000

2002

An early release software product for the rapid development of spoken dialog systems (SDS’s), known as Lyrebird™ [1][2][3], will be demonstrated that makes use of grammatical inference to build natural language, mixed initiative, speech recognition applications. The demonstration will consist of the presenter developing a spoken dialog system using Lyrebird™, and will include a demonstration of some features that are still in the prototype phase.