A case based reasoning model for multilingual language generation in dialogues

The process of Natural Language Generation for a Conversational Agent translates some semantic language to its surface form expressed in natural language. In this paper, we are going to show a Case Based Reasoning technique which is easily extensible and adaptable to multiple domains and languages, that generates coherent phrases and produces a natural outcome in the context of a Conversational Agent that maintains a dialogue with the user.

► We propose a Case Based Reasoning (CBR) method for Natural Language Generation (NLG) in dialogs.
► Grammar and symbolic approaches to NLG have a closed style unuseful for dialogs.
► Symbolic approaches to NLG requires expert knowledge that is expensive to gather.
► The CBR-NLG uses speech acts and templates to get credible and realistic language.
► The CBR-NLG is useful in several languages and domains without expert knowledge.