To improve on this, we combined a BoW model with an RNN-LM, which is faster than the seq2seq models with only a slight sacrifice to model prediction quality. While this approach worked well in terms of prediction quality, it failed to meet our strict latency constraints by orders of magnitude. One approach to include this additional context is to cast the problem as a sequence-to-sequence (seq2seq) machine translation task, where the source sequence is the concatenation of the subject and the previous email body (if there is one), and the target sequence is the current email the user is composing.
In order to incorporate more context about what the user wants to say, our model is also conditioned on the email subject and the previous email body (if the user is replying to an incoming email). In an email, however, the words a user has typed in the current email composing session is only one “signal” a model can use to predict the next word. Typical language generation models, such as ngram, neural bag-of-words (BoW) and RNN language (RNN-LM) models, learn to predict the next word conditioned on the prefix word sequence. Furthermore, researchers had no access to emails, which meant they had to develop and train a machine learning system to work on a dataset that they themselves cannot read. Fairness and Privacy: In developing Smart Compose, we needed to address sources of potential bias in the training process, and had to adhere to the same rigorous user privacy standards as Smart Reply, making sure that our models never expose user’s private information.In order to provide auto completions that are useful for all Gmail users, the model has to have enough modeling capacity so that it is able to make tailored suggestions in subtly different contexts. Scale: Gmail is used by more than 1.4 billion diverse users.Balancing model complexity and inference speed was a critical issue.
0 kommentar(er)
