We have long envisioned that one day computers will understand natural language and
anticipate what we need, when and where we need it, and proactively complete tasks on our …

(Continued) Primary Examiner—Huyen X Vo (74) Attorney, Agent, or Firm—Robert C.
Kowert; Meyertons, Hood, Kivlin, Kowert & Goetzel, PC ABSTRACT A natural language …

(57) ABSTRACT A scalable statistical language understanding (SLU) system uses a fixed
number of understanding models that scale across domains and intents (ie single vs …

As humans, we experience the world with all our senses or modalities (sound, sight, touch,
smell, and taste). We use these modalities, particularly sight and touch, to convey and …

The goal of this paper is to use multi-task learning to efficiently scale slot filling models for
natural language understanding to handle multiple target tasks or domains. The key to …

The recent surge of intelligent personal assistants motivates spoken language
understanding of dialogue systems. However, the domain constraint along with the inflexible …

An important problem in domain adaptation is to quickly generalize to a new domain with
limited supervision given K existing domains. One approach is to retrain a global model …

US10891152B2 - Back-end task fulfillment for dialog-driven applications - Google Patents
US10891152B2 - Back-end task fulfillment for dialog-driven applications - Google Patents …

In natural language understanding (NLU), a user utterance can be labeled differently
depending on the domain or application (eg, weather vs. calendar). Standard domain …

In this paper, we explore the task of map** spoken language utterances to one of
thousands of natural language understanding domains in intelligent personal digital …