Abstract: Text may be modified according to a specified attribute value, such as changing a 1-star review to a 5-star review. To modify the text, an input sequence of tokens may be obtained corresponding to the text. Mask scores may be computed for the tokens by processing the input sequence of tokens with masking neural network. One or more tokens may be selected using the mask scores, and a masked sequence of tokens may be generated by replacing the selected tokens with a mask token. The masked sequence of tokens may be processed by a language model neural network to select a replacement token for each of the mask tokens. Modified text may then be generated using the selected replacement tokens. The modified text may be used for any appropriate application, such as suggesting messages to users participating in a conversation.

Abstract: Text may be modified according to a specified attribute value, such as changing a 1-star review to a 5-star review. To modify the text, an input sequence of tokens may be obtained corresponding to the text. Mask scores may be computed for the tokens by processing the input sequence of tokens with masking neural network. One or more tokens may be selected using the mask scores, and a masked sequence of tokens may be generated by replacing the selected tokens with a mask token. The masked sequence of tokens may be processed by a language model neural network to select a replacement token for each of the mask tokens. Modified text may then be generated using the selected replacement tokens. The modified text may be used for any appropriate application, such as suggesting messages to users participating in a conversation.

Abstract: A social networking system allows its users to provide metadata for association with objects maintained by the social networking system. Some of the metadata may be presented to other users along with the object. To prevent association of inaccurate metadata with an object, the social networking system determines a confidence value associated with a user who provided metadata for association with an object. The confidence value indicates of the accuracy of metadata provided by the user relative to information associated with the object. If the user has previously provided less than a threshold amount of metadata to associate with objects, the confidence score is determined using characteristics associated with the user by the social networking system. The metadata provided by the user is stored but not associated with the object if the user's confidence value is less than a threshold value.

Abstract: A social networking system allows its users to provide metadata for association with objects maintained by the social networking system. Some of the metadata may be presented to other users along with the object. To prevent association of inaccurate metadata with an object, the social networking system determines a confidence value associated with a user who provided metadata for association with an object. The confidence value indicates of the accuracy of metadata provided by the user relative to information associated with the object. If the user has previously provided less than a threshold amount of metadata to associate with objects, the confidence score is determined using characteristics associated with the user by the social networking system. The metadata provided by the user is stored but not associated with the object if the user's confidence value is less than a threshold value.