Beijing Didi Infinity Technology and Development Co., Ltd.

Scot Fang

Kevin Knight

Arkady Arkhangorodsky

Ajay Nagesh

Boliang Zhang

Christopher Chu

Yiqi Huang

Amittai Axelrod

Mariia Ryskina

Xing Shi

Denglin Jiang

An automatic agent may be trained using reinforcement learning. A secret task may be obtained for a simulated user, and the secret task may be unknown to the automatic agent. At least one instruction to complete the secret task may be obtained from the simulated user according to at least one RL policy. At least one action may be generated by the automatic agent based on the at least one instruction and the at least one RL policy. Rewards may be determined for the simulated user and the automatic agent in response to determining that the at least one action successfully completes the secret task. The at least one RL policy may be adjusted based on the determined rewards.

Self-play to improve task-oriented dialog systems and methods

An automatic agent may be improved through feedback. A user input may be received through a user interface. A plurality of current utterance variables may be obtained by tokenizing the user input. The automatic agent may execute a machine learning policy to generate a reply to the user input based on the plurality of current utterance variables. A different reply may be obtained in response to an indication that the reply will lead to a breakdown, wherein the breakdown comprises an unhuman response from the automatic agent according to the machine learning policy. The machine learning policy may be adjusted based on the plurality of current utterance variables and the different reply.

Task-oriented dialog system and method through feedback

Methods, systems, and apparatus, including computer programs encoded on computer storage media for evaluating and improving live translation captioning systems. An exemplary method includes: displaying a word in a first language; receiving a first audio sequence, the first audio sequence comprising a verbal description of the word; generating a first translated text in a second language; displaying the first translated text; receiving a second audio sequence, the second audio sequence comprising a guessed word based on the first translated text; generating a second translated text in the first language; determining a matching score between the word and the second translated text; determining a performance score of the live translation captioning system based on the matching score.

Method and system for evaluating and improving live translation captioning systems

Desired vehicle destinations may be determined from spoken dialogs. A speech input may be received from a user through a voice user interface. Current utterance variables may be obtained by tokenizing the user speech input. One or more of a plurality of utterance templates for a reply to the user speech input may be determined by a trained automatic agent based on the plurality of current utterance variables. One of a plurality of Application Programming Interfaces (API) to call and one or more parameters for the API to call with may be determine by the trained automatic agent based on the plurality of current utterance variables. A response may be obtained from the API call. A context string for the reply to the user speech input by the trained automatic agent may be constructed based on the utterance templates and the response of the API call.

Specifying trip destinations from spoken dialogs

Growing community of inventors

Los Angeles, CA, United States of America

Scot Fang