Dialogue state tracking is the task, in a task-oriented dialogue system, of maintaining the current state of the frame—the fillers of each slot—together with the user's most recent dialogue act. The tracked state includes more than the slot-fillers expressed in the current sentence: it summarizes all of the user's constraints accumulated across the conversation up to this point.

Dialogue State Tracking

A dialogue act represents the interactive function of a turn or sentence within a dialogue, combining the notions of speech act and grounding into a single representation. Dialogue systems use dialogue acts to label and interpret utterances, and different types of dialogue systems require labeling different kinds of dialogue acts.

Saint Olaf College

Google

Dialogue systems, or conversational agents, are programs that communicate with users, through text and/or speech, in natural language.

Dialogue Systems

Every utterance in a dialogue falls under a type of speech act. Knowing the speech act of an utterance is important in understanding the speaker's intention

Speech Acts

Act of the hearer acknowledging that they understood the speaker; this is important in gelling the dialogue into a singular, flowing conversation

Grounding

1) Chatbots

2) Task-oriented dialogue agents

Types of Dialogue Systems

A Frame-based Dialogue System defines a dialogue frame structure and the formatted involved important components.

Frame-based Dialogue System

Language Generation is a sub-field of the field of Natural Language Processing (NLP), Artificial Intelligence (AI) and Cognitive Science (CS).

For natural language generation in the dialogue-state model, its task is to generate the text of the response to the user once a dialogue act has been decided. 

Natural Language Generation (NLG)

Dialogue Act

- Slot-filling, and the simpler tasks of domain and intent classification, are
special cases of the task of supervised semantic parsing,  in which we have a training set that associates each sentence with the correct set of slots, domain, and intent.
- A simple method is to train a sequence model to map from input word representation to slot fillers, domain, and intent.


Slots Filling

Chatbots and task-oriented dialogue agents are evaluated on different metrics; chatbots are scored on how the user feels when interacting with the program, whereas task-oriented systems are scored based on their ability to complete a task.

Evaluating Dialogue Systems

1) Constatives -> asserts that something is either true or false (answering, claiming, disagreeing, denying)


2) Directives -> attempt by speaker to get hearer to do something (asking, ordering, inviting)


3) Commissives -> commits the speaker to some future action (promising, planning, vowing)


4) Acknowledgments -> expresses the speaker's feelings towards the hearer regarding some action (thanking, apologizing, greeting)

Learn Before

Related

Learn After