Depending on the type of application or Dialogue System you’re creating, you have multiple tools, components, and architectures that can be utilized to achieve your vision. Under the Resources tab, there are various components, tools, and architectures that are listed, as well as any helpful links on installation, customization, and even integration. Below is a list of the various Resources provided by DialPort and what they entail:
This page provides a list of Dialogue System architectures that can be used as a reference.
This page provides various Dialogue Managers. A dialogue manager is responsible for the state and flow of the conversation.
Natural Language Processing Toolkits
A list of toolkits for Natural Language Processing (NLP). Each toolkit has various tools that can tackle different activities.
Natural Language Understanding
NLU (Natural Language Understanding) tools are used to understand user input and take appropriate actions based on that understanding.
Machine Learning Tools
Machine learning is often used for various parts of a dialogue system, for example speech act classification as part of natural language understanding.
Natural Language Generation
Natural Language Generation is the natural language processing task of generating natural language from a machine representation system such as a knowledge base or a logical form.
ASR (Automatic Speech Recognizer) tools allow spoken words in various languages (depending on the software) to be transcribed into words and sentences.
Text to Speech Tools
TTS (Text to Speech) Tools translate text into spoken audio.
A parser is a software component that takes input data (frequently text) and builds a data structure – often some kind of parse tree, abstract syntax tree or other hierarchical structure – giving a structural representation of the input, checking for correct syntax in the process.
Tools to help with annotating sets of data.
Tools that help with authoring new systems.
WoZ (Wizard of Oz) systems allow a human to choose response that the machine will output from a fixed domain of possible responses.