3 papers
cs.CL2023
End-to-End Autoregressive Retrieval via Bootstrapping for Smart Reply Systems
Benjamin Towle, Ke Zhou
Reply suggestion systems represent a staple component of many instant messaging and email systems. However, the requirement to produce sets of replies, rather than individual repli…
cs.CL2023
Model-Based Simulation for Optimising Smart Reply
Benjamin Towle, Ke Zhou
Smart Reply (SR) systems present a user with a set of replies, of which one can be selected in place of having to type out a response. To perform well at this task, a system should…
cs.CL2023
Learn What Is Possible, Then Choose What Is Best: Disentangling One-To-Many Relations in Language Through Text-based Games
Benjamin Towle, Ke Zhou
Language models pre-trained on large self-supervised corpora, followed by task-specific fine-tuning has become the dominant paradigm in NLP. These pre-training datasets often have…