Mon 24 Jun 2019 16:40 - 17:00 at 224AB - Parsing Chair(s): Qirun Zhang

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.

Mon 24 Jun

pldi-2019-papers
16:00 - 17:00: PLDI Research Papers - Parsing at 224AB
Chair(s): Qirun ZhangGeorgia Institute of Technology
pldi-2019-papers16:00 - 16:20
Talk
Rijnard van TonderCarnegie Mellon University, Claire Le GouesCarnegie Mellon University
DOI Pre-print Media Attached
pldi-2019-papers16:20 - 16:40
Talk
Neel KrishnaswamiComputer Laboratory, University of Cambridge, Jeremy YallopUniversity of Cambridge, UK
Link to publication DOI Pre-print
pldi-2019-papers16:40 - 17:00
Talk
Giovanni CampagnaStanford University, USA, Silei Xu, Mehrad MoradshahiStanford University, USA, Richard SocherSalesforce, USA, Monica S. LamStanford University, USA
Media Attached