A Dataset and Baselines for Multilingual Reply Suggestion
Reply suggestion models help users process emails and chats faster. Previous work only studies English reply suggestion. Instead, we present MRS, a multilingual reply suggestion dataset with ten languages. MRS can be used to compare two families of models: 1) retrieval models that select the reply from a fixed set and 2) generation models that produce the reply from scratch. Therefore, MRS complements existing cross-lingual generalization benchmarks that focus on classification and sequence labeling tasks. We build a generation model and a retrieval model as baselines for MRS. The two models have different strengths in the monolingual setting, and they require different strategies to generalize across languages. MRS is publicly available at https://github.com/zhangmozhi/mrs.
Code (1)
Tasks
RetrievalSimilar Papers 제목 키워드 기반
A Conditional Generative Matching Model for Multi-lingual Reply Suggestion
We study the problem of multilingual automated reply suggestions (RS) model serving many languages simultaneously. Multilingual models are often challenged by model capacity and severe data distribution skew across langu…
DiversityEnd-to-End Autoregressive Retrieval via Bootstrapping for Smart Reply Systems
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…
DiversityRetrievalText RetrievalExploring Low-Cost Transformer Model Compression for Large-Scale Commercial Reply Suggestions
Fine-tuning pre-trained language models improves the quality of commercial reply suggestion systems, but at the cost of unsustainable training times. Popular training time reduction approaches are resource intensive, thu…
Model CompressionPragAlign: Evidence-Sensitive Reply Assistance Across Chinese and Japanese Appropriateness Judgments
Reply assistance in multilingual settings requires linguistic competence and culturally situated judgments of appropriateness. We present PragAlign, which separates context reading from selective clarification, and evalu…
Smart Reply: Automated Response Suggestion for Email
In this paper we propose and investigate a novel end-to-end method for automatically generating short email responses, called Smart Reply. It generates semantically diverse suggestions that can be used as complete email …
ClusteringDiversity