Abstract
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.- Anthology ID:
- 2023.findings-emnlp.510
- Volume:
- Findings of the Association for Computational Linguistics: EMNLP 2023
- Month:
- December
- Year:
- 2023
- Address:
- Singapore
- Editors:
- Houda Bouamor, Juan Pino, Kalika Bali
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 7610–7622
- Language:
- URL:
- https://aclanthology.org/2023.findings-emnlp.510
- DOI:
- 10.18653/v1/2023.findings-emnlp.510
- Cite (ACL):
- Benjamin Towle and Ke Zhou. 2023. End-to-End Autoregressive Retrieval via Bootstrapping for Smart Reply Systems. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 7610–7622, Singapore. Association for Computational Linguistics.
- Cite (Informal):
- End-to-End Autoregressive Retrieval via Bootstrapping for Smart Reply Systems (Towle & Zhou, Findings 2023)
- PDF:
- https://preview.aclanthology.org/aacl-23-doi-ingestion/2023.findings-emnlp.510.pdf