Methods, systems, and media for presenting user comments containing timed references in synchronization with a media content item

    公开(公告)号:US12074925B2

    公开(公告)日:2024-08-27

    申请号:US17666459

    申请日:2022-02-07

    Applicant: Google LLC

    CPC classification number: H04L65/4015 H04L51/046 H04L51/212 H04L51/216

    Abstract: Methods, systems, and media for presenting user comments containing timed references in synchronization with a media content item are provided. In some embodiments, a method for presenting user comments during media playback that includes: obtaining a plurality of comments associated with a media content item; determining a subset of comments from the plurality of comments that contains at least one of a plurality of timed references to the media content item; determining a series of time windows, wherein each time window in the series of time windows corresponds to a segment of the media content item; associating one or more comments from the subset of comments with a time window from the series of time windows, wherein the time window contains a time referenced in a comment; receiving a request to receive comments that are synchronized with playback of the media content item; and, in response to receiving the request to receive comments that are synchronized with playback of the media content item, causing a first comment associated with a first time window to be presented concurrently with a first portion of the media content item that corresponds with the first time window and a second comment associated with a second time window to be presented concurrently with a second portion of the media content item that corresponds with the second time window.

    Dataset Refining with Machine Translation Quality Prediction

    公开(公告)号:US20230025739A1

    公开(公告)日:2023-01-26

    申请号:US17852863

    申请日:2022-06-29

    Applicant: Google LLC

    Abstract: Aspects of the technology employ a machine translation quality prediction (MTQP) model to refine datasets that are used in training machine translation systems. This includes receiving, by a machine translation quality prediction model, a sentence pair of a source sentence and a translated output (802). Then performing feature extraction on the sentence pair using a set of two or more feature extractors, where each feature extractor generates a corresponding feature vector (804). The corresponding feature vectors from the set of feature extractors are concatenated together (806). And the concatenated feature vectors are applied to a feedforward neural network, in which the feedforward neural network generates a machine translation quality prediction score for the translated output (808).

    METHODS, SYSTEMS, AND MEDIA FOR PRESENTING USER COMMENTS CONTAINING TIMED REFERENCES IN SYNCHRONIZATION WITH A MEDIA CONTENT ITEM

    公开(公告)号:US20230254350A1

    公开(公告)日:2023-08-10

    申请号:US17666459

    申请日:2022-02-07

    Applicant: Google LLC

    CPC classification number: H04L65/4015 H04L51/16 H04L51/12 H04L51/046

    Abstract: Methods, systems, and media for presenting user comments containing timed references in synchronization with a media content item are provided. In some embodiments, a method for presenting user comments during media playback that includes: obtaining a plurality of comments associated with a media content item; determining a subset of comments from the plurality of comments that contains at least one of a plurality of timed references to the media content item; determining a series of time windows, wherein each time window in the series of time windows corresponds to a segment of the media content item; associating one or more comments from the subset of comments with a time window from the series of time windows, wherein the time window contains a time referenced in a comment; receiving a request to receive comments that are synchronized with playback of the media content item; and, in response to receiving the request to receive comments that are synchronized with playback of the media content item, causing a first comment associated with a first time window to be presented concurrently with a first portion of the media content item that corresponds with the first time window and a second comment associated with a second time window to be presented concurrently with a second portion of the media content item that corresponds with the second time window.

Patent Agency Ranking