Systems and methods for providing responses from media content

An electronic device, comprising:

• one or more processors;
• and
• memory storing one or more programs, the one or more programs including instructions for:
• retrieving, from a database, a plurality of transcripts, each transcript in the plurality of transcripts corresponding to audio from a media content item of a plurality of media content items that are provided by a media providing service;
• applying each transcript of the plurality of transcripts to a trained computational model;
• receiving a user request for information regarding a topic, wherein the user request includes a string of words;
• and
• in response to the user request:
• identifying, by applying the string of words to the trained computational model:
• a transcript from the database that is relevant to the topic;
• a position within the transcript that is relevant to the topic;
• and
• causing playback of at least a portion of a media content item corresponding to the identified transcript, beginning at a starting position that is based on the position within the identified transcript that is relevant to the topic,
• wherein:
• the trained computational model is trained, using a training set of questions and answers, to provide a position within a known text source in response to receiving a user request for information;
• and
• the training set of questions and answers is distinct and separate from the plurality of transcripts.

A non-transitory computer-readable storage medium storing one or more programs, the one or more programs including instructions that, when executed by an electronic device with one or more processors, cause the electronic device to:

• retrieve, from a database, a plurality of transcripts, each transcript in the plurality of transcripts corresponding to audio from a media content item of a plurality of media content items that are provided by a media providing service;
• apply each transcript of the plurality of transcripts to a trained computational model;
• receive a user request for information regarding a topic, wherein the user request includes a string of words;
• and
• in response to the user request:
• identify, by applying the string of words to the trained computational model:
• a transcript from the database that is relevant to the topic;
• a position within the transcript that is relevant to the topic;
• and
• cause playback of at least a portion of a media content item corresponding to the identified transcript, beginning at a starting position that is based on the position within the identified transcript that is relevant to the topic,
• wherein:
• the trained computational model is trained, using a training set of questions and answers, to provide a position within a known text source in response to receiving a user request for information;
• and
• the training set of questions and answers is distinct and separate from the plurality of transcripts.