YouTube has launched SmartReply built for creators and implemented in YouTube Studio that helps creators engage more easily with their viewers.
This model learns comment and reply representation through a computationally dilated self-attention network, and represents a cross-lingual and character byte-based SmartReply model.
SmartReply for YouTube is currently available for English and Spanish creators, and this approach simplifies the process of extending the SmartReply feature to many more languages in the future.
YouTube creators receive a large volume of responses to their videos and, the community of creators and viewers on YouTube is diverse, as reflected by their comments, discussions, and videos.
In comparison to emails, which tend to be long and dominated by formal language, YouTube comments reveal complex patterns of language switching, abbreviated words, slang, inconsistent usage of punctuation, and heavy utilization of emoji. Following is a sample of comments that illustrate this challenge:
To tackle this YouTube developed a model, by also applying learnings from the previous launches of SmartReply on other Google products such as Gmail.
Ideally, suggestions would only be displayed when it is likely that the creator would reply to the comment, and when the model has a high chance of providing a sensible and specific response. To accomplish this, auxiliary models have been trained to identify which comments should trigger the SmartReply feature.
YouTube SmartReply has been launched in English and Spanish comments, the first cross-lingual and character byte-based SmartReply. YouTube has a diverse user base that generates heterogeneous content. Consequently, the platform will improve comments and SmartReply for the global audience.