An NLG pipeline for a legal expert system: a work in progress
This work addresses the need for domain-specific natural language generation in legal applications, but it is incremental as it builds on existing methods without introducing major innovations.
The authors tackled the problem of generating natural language for a legal expert system by developing an NLG pipeline that creates interviews and renders automated reasoning results, but no concrete performance numbers or results were provided.
We present the NLG component for L4, a prototype domain-specific language (DSL) for drafting laws and contracts. As a concrete use case, we describe a pipeline for a legal expert system created from L4 code. The NLG component is used in two steps. The first step is to create an interview, whose answers are processed into a query for an automated reasoner. The second step is to render the answers of the reasoner in natural language.