This thesis is about natural language parsing with corpus-based grammars that
are enriched with statistics. Parsing is the process of analysing the syntactic
structure of an utterance. The role of statistics is to improve the parsing process. Our research is done in the context of the SCHISMA project, in which a
natural language dialogue system for theatre information and booking services
is developed.

Towards Probabilistic Unification-Based Parsing

This chapter describes Conversational Agents (CAs) in the context of Systems Engineering. A CA is a computer program which interacts with a user through natural language dialogue and provides some form of service. CA technology has two points of interest to systems engineers: the use of systems engineering techniques in CA research and the application of CAs in project development. CAs offer the opportunity to automate more complex applications than are feasible with conventional web interfaces. Currently such applications require a human expert in the domain to mediate between the user and the application. The CA effectively replaces the human expert. This chapter reviews the current capabilities of various CA technologies, outlines a development methodology for systems engineering practitioners interested in developing real world applications and suggests a number of directions for systems engineers who wish to participate in CA research.

/pdf/systems-engineering-and-conversational-agents-1lpek7c0qf.pdf

Systems Engineering and Conversational Agents

Problem statement: Feature selection is a task of crucial importance for the application of
machine learning in various domains. In addition, the recent increase of data dimensionality poses a
severe challenge to many existing feature selection approaches with respect to efficiency and
effectiveness. As an example, genetic algorithm is an effective search algorithm that lends itself
directly to feature selection; however this direct application is hindered by the recent increase of data
dimensionality. Therefore adapting genetic algorithm to cope with the high dimensionality of the data
becomes increasingly appealing. Approach: In this study, we proposed an adapted version of genetic
algorithm that can be applied for feature selection in high dimensional data. The proposed approach is
based essentially on a variable length representation scheme and a set of modified and proposed
genetic operators. To assess the effectiveness of the proposed approach, we applied it for cues phrase
selection and compared its performance with a number of ranking approaches which are always
applied for this task. Results and Conclusion: The results provide experimental evidences on the
effectiveness of the proposed approach for feature selection in high dimensional data.

/pdf/feature-selection-for-high-dimensional-data-an-evolutionary-5f2esw8abq.pdf

Feature selection for high dimensional data: An evolutionary filter approach.

This dissertation presents and evaluates a method of managing spoken dialog interactions with a robust attention to fulfilling the human user’s goals in the presence of speech recognition limitations. Assistive speech-based embodied conversation agents are computer-based entities that interact with humans to help accomplish a certain task or communicate information via spoken input and output. A challenging aspect of this task involves open dialog, where the user is free to converse in an unstructured manner. With this style of input, the machine’s ability to communicate may be hindered by poor reception of utterances, caused by a user’s inadequate command of a language and/or faults in the speech recognition facilities. Since a speech-based input is emphasized, this endeavor involves the fundamental issues associated with natural language processing, automatic speech recognition and dialog system design. Driven by ContextBased Reasoning, the presented dialog manager features a discourse model that implements mixed-initiative conversation with a focus on the user’s assistive needs. The discourse behavior must maintain a sense of generality, where the assistive nature of the system remains constant regardless of its knowledge corpus. The dialog manager was encapsulated into a speech-based embodied conversation agent platform for prototyping and testing purposes. A battery of user trials was performed on this agent to evaluate its performance as a robust, domain-independent, speech-based interaction entity capable of satisfying the needs of its users.

/pdf/robust-dialog-management-through-a-context-centric-1hunmvzuiz.pdf

Robust Dialog Management Through A Context-centric Architecture

This paper addresses the application of dialogue management techniques in a buyer-seller situation. In particular, we will describe the techniques used in the SCHISMA system, a system that provides the caller with information on theatre performances, and optionally "sells" the caller one or more tickets for a given performance.

Building dialogue systems that sell

SCHISMA is a joint research project of KPN (Royal PTT Nederland) and the University of Twente. The
project aims at providing a natural language dialogue system which interfaces a database containing
information about theatre performances in a certain city or region. The interface should make it possible
to ask about performances in general, to tune in to a specific performance and, if desired, make a
reservation for this performance. Research until now has concentrated on various aspects of realising
such a theatre information and booking system. Among these aspects are the building of a Wizard of Oz
environment for the acquisition of a corpus of dialogues for this domain, analysis and tagging of the
dialogue corpus, recognition of domain-specific concepts (actors, authors, plays, dates, etc.), syntactic
analysis and dialogue modelling. The emphasis in this paper will be on the analysis of individual
utterances at various levels. Most important for the project are short and medium term goals of delivering
prototype systems that allow demonstration of the system and evaluation of the design choices. Due to
these goals the project does not strive at incorporating advanced but isolated research results on discourse
models and syntactic and semantic analysis. Rather we investigate how to identify user preferences and
how to embed systems like these in a more comprehensive environment of information and transaction
services.

Language analysis for dialogue management in a theatre information and booking system

The analysis of natural language in the context of keyboard-driven dialogue systems is the central issue addressed in this paper. A module that corrects typing errors, performs domain-specific morphological analysis is developed. A parser for typed unification grammars has been designed and implemented in C++; for description of the lexicon and the grammar a suitable specification language has been developed. It is argued that typed unification grammars and especially the newly developed specification language are convenient formalisms for describing natural language use in dialogue systems. Finally we present a dialogue manager that is based on a finite state automaton; transitions in the automaton depend upon availability of information in utterances of the user. In order to keep track of the history of the dialogue, a context stack is constructed during the dialogue. The manager is implemented in Prolog.

Language Engineering in Dialogue Systems

An importantpart of dialoguemanagementin a dialoguesystemis topic managementThe systemhas to keep track of topic aspects (current topic, context, obligations,. . .) in order to be able to resolve ambiguities and to respond in a cooperative and sensible way. In the project, we are developing a system that takes part in a conversation about theater performances and is able to make ticket reservations. In this paper we discuss several techniques for topic management that we developed and tested this year. 1. Introduction In a dialogue system one of the main tasks is answering questions that the user states, either explicitly or implicitly. Since the question is often based on, or referring to, earlier utterances of either speaker, analyzing only the last user utterance will not suffice in most cases. This conjecture is verified in the SCHISMA project, a cooperative project of Twente University and KPN Research in the Netherlands. In this project the SCHISMA system is developed. It provides the user with information on theater

H.W.L. ter Doest

Papers

Language analysis for dialogue management in a theatre information and booking system

Language Engineering in Dialogue Systems

Dialogues in a theatre information and booking system