Natural Language Dialogue Architectures for Tactical Questioning Characters

Abstract

In this paper we contrast three architectures for natural language questioning characters. We contrast the relative costs and benefits of each approach in building characters for tactical questioning. The first architecture works purely at the textual, using cross-language information retrieval techniques to learn the best output for any input from a training set of linked questions and answers. The second architecture adds a global emotional model and computes a compliance model, which can result in different outputs for different levels, given the same inputs. The third architecture works at a semantic level and allows authoring of different policies for response for different kinds of information. We describe these architectures and their strengths and weaknesses with respect to expressive capacity, performance, and authoring demands.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Dec 01, 2008
Accession Number
ADA503947

Entities

People

  • Anton Leuski
  • Antonio Roque
  • Bilyana Martinovski
  • David Devault
  • David R Traum
  • Jillian Gerten
  • Sudeep Gandhe
  • Susan Robinson

Organizations

  • University of Southern California

Tags

Communities of Interest

  • Energy and Power Technologies
  • Human Systems

DTIC Thesaurus Topics

  • Accuracy
  • Automated Speech Recognition
  • Dialogue Systems
  • Governments
  • Information Retrieval
  • Language
  • Military Personnel
  • Motivation
  • Multiagent Systems
  • Natural Languages
  • New York
  • Personality
  • Personnel Management
  • Security
  • Trainees
  • United States
  • United States Government

Fields of Study

  • Computer science

Readers

  • Artificial Intelligence
  • Computational Linguistics
  • Strategic Security Studies

Technology Areas

  • AI & ML
  • AI & ML - Information Retrieval
  • AI & ML - Machine Translation
  • AI & ML - Neural Networks