Genie: A Generator of Natural Language Semantic Parsers for Virtual Assistant Commands
To understand diverse natural language commands, virtual assistants today are trained with numerous labor-intensive, manually annotated sentences. This paper presents a methodology and the Genie toolkit that can handle new compound commands with significantly less manual effort.
We advocate formalizing the capability of virtual assistants with a Virtual Assistant Programming Language (VAPL) and using a neural semantic parser to translate natural language into VAPL code. Genie needs only a small realistic set of input sentences for validating the neural model. Developers write templates to synthesize data; Genie uses crowdsourced paraphrases and data augmentation, along with the synthesized data, to train a semantic parser.
We also propose design principles that make VAPL languages amenable to natural language translation. We apply these principles to revise ThingTalk, the language used by the Almond virtual assistant. We use Genie to build the first semantic parser that can support compound virtual assistants commands with unquoted free-form parameters. Genie achieves a 62% accuracy on realistic user inputs. We
demonstrate Genie’s generality by showing a 19% and 31% improvement over the previous state of the art on a music skill, aggregate functions, and access control.
Conference DayMon 24 JunDisplayed time zone: Tijuana, Baja California change
16:00 - 17:00
|Lightweight Multi-Language Syntax Transformation with Parser Parser Combinators|
PLDI Research PapersDOI Pre-print Media Attached
|A Typed, Algebraic Approach to Parsing|
PLDI Research Papers
Neel KrishnaswamiComputer Laboratory, University of Cambridge, Jeremy YallopUniversity of Cambridge, UKLink to publication DOI Pre-print
|Genie: A Generator of Natural Language Semantic Parsers for Virtual Assistant Commands|
PLDI Research Papers
Giovanni CampagnaStanford University, USA, Silei Xu, Mehrad MoradshahiStanford University, USA, Richard SocherSalesforce, USA, Monica S. LamStanford University, USAMedia Attached