Soco, Inc.

Other

Tiancheng Zhao

Kyusong Lee

Yilian Liu

Systems and methods involving SPARTA (Sparse Transformer Matching) are disclosed. Embodiments may relate to scalable and transferable retrieval methods for question answering.

Question answering retrieval via sparse transformer matching

A system and method of creating the natural language understanding component of a speech/text dialog system. The method involves a first step of defining user intent in the form of an intent flow graph. Next, (context, intent) pairs are created from each of the plurality of intent flow graphs and stored in a training database. A paraphrase task is then generated from each (context, intent) pair and also stored in the training database. A zero-shot intent recognition model is trained using the plurality of (context, intent) pairs in the training database to recognize user intents from the plurality of paraphrase tasks in the training database. Once trained, the zero-shot intent recognition model is applied to user queries to generate semantic outputs.

System and method for defining dialog intents and building zero-shot intent recognition models

Techniques for dialog data collection are disclosed. In an embodiment, a method comprises providing a first graphical user interface () configured to receive first user input data, providing a second graphical user interface () configured to receive second user input data, asynchronously transmitting the first user input data to the second graphical user interface () or the second user input data to the first graphical user interface (), and generating training data for a natural language processing system model () based on the first user input data and the second user input data.

Growing community of inventors

Pittsburgh, PA, United States of America

Tiancheng Zhao