1.1. Overview
Explain components, properties, scopes, techniques, and assessments of dialogue systems.
Conversation: interactive communication between two or more people.
Dialogue: a conversation, often between two people, with a specific goal in mind.
Dialog: a window that appears on a screen in computing contexts (e.g., dialog box).
Dialogue System: a computer system that interacts with humans in natural language.
Conversational Agent: a dialogue system that interprets and responds to user statements.
Virtual Assistant: a dialogue system that performs tasks or services for user requests.
Dialogue Management: a process of controlling the state and flow of the dialogue to conduct contextual communications.
Conversational AI: a type of Artificial Intelligence (AI) for a dialogue system to understand user inputs and respond properly to them, often processed by machine learning models.
What are examples of dialogue systems currently used in practical applications?
Are there applications that would greatly benefit from adopting dialogue systems?
Turn: a single contribution from one speaker to the dialogue.
Utterance: a natural unit of speech bounded by breaths or pauses.
Speech Act: the action, either explicitly or implicitly, expressed by an utterance (e.g., answering, advising, greeting; see ).
Intent: the user's goal expressed by an utterance within the context of a conversation (e.g., making an appointment, requesting information).
Topic: the matter dealt with in an utterance (e.g., movie, family, midterm).
Classify each of the following utterances from Friends S1E1 using the dialogue acts:
Ross: Hi.
Joey: This guy says hello, I wanna kill myself.
Monica: Are you okay, sweetie?
Ross: I just feel like someone reached down my throat, grabbed my small intestine, pulled it out of my mouth and tied it around my neck...
Chandler
Task-oriented dialogue systems have specific tasks to be accomplished:
, Henderson et al., SIGDIAL, 2014 ().
, Wen et al., EMNLP 2016 ().
, Bordes et al., ICLR, 2017 ().
Open-domain dialogue systems aim to talk about any topics without specific end goals:
What kind of tasks are presented in the above task-oriented datasets?
Try the demos of BlenderBot and ChatGPT. What are their limitations?
What are the challenges in building task-oriented vs. open-domain dialogue systems?
A dialogue flow can be designed into a fine-state machine. Most commercial dialogue systems take this approach because it gives greater control over how the systems behave. Several platforms are available to facilitate the development of state machine-based dialogue systems:
Recent researches focus on developing end-to-end dialogue systems using sequence-to-sequence (S2S) models, which is a type of encoder-decoder model:
, Sutskever et al., NeurIPS, 2014.
The current state-of-the-art S2S models use transformers such as BERT as their encoders:
, Vaswani et al., NeurIPS, 2017.
, Devlin et al., NAACL, 2019.
Three of the above, Meta BlenderBot, OpenAI ChatGPT, and Google LaMDA, are end-to-end systems based on S2S models.
The primary objective of both task-oriented and open-domain dialogue systems is to satisfy users by communicating with them. For task-oriented, users are generally satisfied if the tasks are accomplished efficiently. For open-domain, however, user satisfaction is often highly subjective, so proper conversational analysis may need to be involved.
, Finch and Choi, SIGDIAL, 2020.
, Mehri et al., arXiv, 2022.
, Finch et al., arXiv, 2022.
