CLAILGOct 29, 2023

End-to-End Autoregressive Retrieval via Bootstrapping for Smart Reply Systems

arXiv:2310.18956v1131 citationsh-index: 2
Originality Incremental advance
AI Analysis

This addresses the challenge of producing diverse reply sets in messaging and email systems, which is an incremental improvement over existing retrieval-based methods.

The paper tackles the problem of generating diverse and relevant reply sets in smart reply systems by introducing an end-to-end autoregressive retrieval model trained on bootstrapped data, achieving improvements of 5.1%-17.9% in relevance and 0.5%-63.1% in diversity over state-of-the-art baselines.

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 replies, makes the task poorly suited for out-of-the-box retrieval architectures, which only consider individual message-reply similarity. As a result, these system often rely on additional post-processing modules to diversify the outputs. However, these approaches are ultimately bottlenecked by the performance of the initial retriever, which in practice struggles to present a sufficiently diverse range of options to the downstream diversification module, leading to the suggestions being less relevant to the user. In this paper, we consider a novel approach that radically simplifies this pipeline through an autoregressive text-to-text retrieval model, that learns the smart reply task end-to-end from a dataset of (message, reply set) pairs obtained via bootstrapping. Empirical results show this method consistently outperforms a range of state-of-the-art baselines across three datasets, corresponding to a 5.1%-17.9% improvement in relevance, and a 0.5%-63.1% improvement in diversity compared to the best baseline approach. We make our code publicly available.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes