Conversational user interface: Difference between revisions

Revision as of 12:46, 15 October 2020

Revision as of 13:27, 18 October 2020

Line 2:

A '''conversational interface''' (CUI) is a [[user interface]] for computers that emulates a conversation with a real human. Historically, computers have relied on [[text-based user interface]]s and [[graphical user interface]]s (GUIs) (such as the user pressing a "back" button) to translate the user's desired action into commands the computer understands. While an effective mechanism of completing computing actions, there is a learning curve for the user associated with GUI.<ref>{{cite web |title=Conversational Interfaces: Where Are We Today? Where Are We Heading? |website=Smashing Magazine |url=https://www.smashingmagazine.com/2016/07/conversational-interfaces-where-are-we-today-where-are-we-heading/ |ref={{SfnRef|Smashing Magazine}} |access-date=2018-05-23}}</ref> Instead, CUIs provide opportunity for the user to communicate with the computer in their natural language rather than in a syntax specific commands. <ref>{{cite web |last=Brownlee |first=John |title=Conversational Interfaces, Explained |website=Co.Design |date=2016-04-04 |url=https://www.fastcodesign.com/3058546/conversational-interfaces-explained |ref=harv |access-date=2018-05-23}}</ref>

To do this, conversational interfaces use [[natural language processing]] (NLP) to allow computers to understand, analyze, and create meaning from human language. Unlike word processors, NLP considers the structure of human language (i.e., words make phrases; phrases make sentences which convey the idea or intent the [[user (computing)|user]] is trying to invoke). The ambiguous nature of human language makes it difficult for a machine to always correctly interpret the user's requests, which is why we have seen a shift toward [[natural-language understanding]] (NLU).<ref>{{cite web |last=Pan |first=Jiaqi |title=Conversational Interfaces: The Future of Chatbots – Chatbots Magazine |website=Chatbots Magazine |date=2017-08-25 |url=https://chatbotsmagazine.com/conversational-interfaces-the-future-of-chatbots-18975a91fe5a |ref=harv |access-date=2018-05-23}}</ref>.

NLU allows for [[sentiment analysis]] and conversational searches which allows a line of questioning to continue, with the [[context (language use)|context]] carried throughout the conversation. NLU allows conversational interfaces to handle unstructured inputs that the human brain is able to understand such as spelling mistakes of follow-up questions.<ref>{{cite web |author=Lola |title=NLP vs. NLU: What's the Difference? – Lola – Medium |website=Medium |date=2016-10-05 |url=https://medium.com/@lolatravel/nlp-vs-nlu-whats-the-difference-d91c06780992 |ref=harv |access-date=2018-05-23}}</ref> For example, through leveraging NLU, a user could first ask for the population of the United States. If the user then asks "Who is the president?", the search will carry forward the context of the United States and provide the appropriate response.