Dialog-Centered System

A Dialog-Centered System is a conversational-centered system that can solve a automated dialog-centered tasks (by performing dialog acts).

• Context:
  • It can contribute to a Conversational Session.
  • It can range from being a Automated Conversational System to being an Embodied Conversational Agent.
  • It can range from being a Goal-Oriented Conversational System to being a Small-Talk Conversational System.
  • It can be based on a Conversational System Platform.
  • It can (often) contain a Dialog Manager.
  • …
• Example(s):
  • a Question Answering System.
  • a Spoken Dialog System.
  • a Medical Dialogue System.
  • DA systems: Nuance (bNuance+PhoneticSystems), BBN/Nortel, TellMe/Microsoft, Jingle, Google, AT&T, IBM (mid 1990s)
  • Dictation/speech to text systems: Dragon (mid1990s)
  • TV close captioning BBN/NHK (early 2000s)
  • Automated attendant & Call routing: AT&T, BBN, Nuance, IBM (early 2000s)
  • Form-filling directed dialog (flight reservations) (early 2000s)
  • Personal assistants/Full web search: Siri/Apple, Dragon Go, Google Voice, Vlingo/SVoice, Microsoft Cortana (from 2008)].
  • Character.AI Service.
  • …
• Counter-Example(s):
  • a Conversing Human.
  • a Question Answering System.
  • a Linguistic-Input Only System.
  • a Linguistic-Output Only System.
• See: GUI, Wizard (Software), Wizard (Software), GUI.

---

---

References

2023

• (Wikipedia, 2023) ⇒ https://en.wikipedia.org/wiki/Dialogue_system Retrieved:2023-7-20.
  • A dialogue system, or conversational agent (CA), is a computer system intended to converse with a human. Dialogue systems employed one or more of text, speech, graphics, haptics, gestures, and other modes for communication on both the input and output channel.

    The elements of a dialogue system are not defined because this idea is under research,however, they are different from chatbot. The typical GUI wizard engages in a sort of dialogue, but it includes very few of the common dialogue system components, and the dialogue state is trivial.

2023

• https://beta.character.ai/help
  • QUOTE: ... Character.AI is bringing to life the science-fiction dream of open-ended conversations and collaborations with computers.

    We are building the next generation of dialog agents — with a long-tail of applications spanning entertainment, education, general question-answering and others. ...

2020

• (Wikipedia, 2020) ⇒ https://en.wikipedia.org/wiki/Virtual_assistant Retrieved:2020-12-21.
  • … Users can ask their assistants questions, control home automation devices and media playback via voice, and manage other basic tasks such as email, to-do lists, and calendars with verbal (spoken?) commands. A similar concept, however with differences, lays under the dialogue systems.

2020

• (Falke et al., 2020) ⇒ Tobias Falke, Markus Boese, Daniil Sorokin, Caglar Tirkaz, and Patrick Lehnen. (2020). “Leveraging User Paraphrasing Behavior In Dialog Systems To Automatically Collect Annotations For Long-Tail Utterances.” In: Proceedings of the 28th International Conference on Computational Linguistics: Industry Track.
  • ABSTRACT: In large-scale commercial dialog systems, users express the same request in a wide variety of alternative ways with a long tail of less frequent alternatives. Handling the full range of this distribution is challenging, in particular when relying on manual annotations. However, the same users also provide useful implicit feedback as they often paraphrase an utterance if the dialog system failed to understand it. We propose MARUPA, a method to leverage this type of feedback by creating annotated training examples from it. MARUPA creates new data in a fully automatic way, without manual intervention or effort from annotators, and specifically for currently failing utterances. By re-training the dialog system on this new data, accuracy and coverage for long-tail utterances can be improved. In experiments, we study the effectiveness of this approach in a commercial dialog system across various domains and three languages.

2017

• (Wikipedia, 2017) ⇒ https://en.wikipedia.org/wiki/Dialog_system#Components Retrieved:2017-4-5.
  • There are many different architectures for dialog systems. What sets of components are included in a dialog system, and how those components divide up responsibilities differs from system to system. Principal to any dialog system is the dialog manager, which is a component that manages the state of the dialog, and dialog strategy. A typical activity cycle in a dialog system contains the following phases:
    1. The user speaks, and the input is converted to plain text by the system's input recognizer/decoder, which may include:
       • automatic speech recognizer (ASR)
       • gesture recognizer.
       • handwriting recognizer.
    2. The text is analyzed by a Natural language understanding unit (NLU), which may include:
       • Proper Name identification
       • part of speech tagging
       • Syntactic/semantic parser.
    3. The semantic information is analyzed by the dialog manager, that keeps the history and state of the dialog and manages the general flow of the conversation.
    4. Usually, the dialog manager contacts one or more task managers, that have knowledge of the specific task domain.
    5. The dialog manager produces output using an output generator, which may include:
       • natural language generator.
       • gesture generator.
       • layout engine.
    6. Finally, the output is rendered using an output renderer, which may include:
       • text-to-speech engine (TTS).
       • talking head.
       • robot or avatar.
  • Dialog systems that are based on a text-only interface (e.g. text-based chat) contain only stages 2–5.

2014a

• (Quinn, 2014) ⇒ Kevin Quinn. (2014). “ANA: Automated Nursing Agent." Master's Thesis, University of Alberta.

2014b

• Dan Jurafsky. (2014). “Conversational Agents." Presentation from CS124 - From Languages to Information.

2000

• (Ball & Breese, 2000) ⇒ Gene Ball, and Jack Breese. (2000). “Emotion and Personality in a Conversational Agent." Embodied conversational agents
• (Cassell, 2000) ⇒ Justine Cassell. (2000). “Embodied Conversational Agents." MIT press,

---