轻量级MLP模型修复不完整对话，提升上下文理解
RSMLP: A light Sampled MLP Structure for Incomplete Utterance Rewrite
- 用采样策略优化MLP结构，高效提取语义信息
- 在公开数据集和真实场景中表现优异
- 适合资源受限的对话系统部署
不完整话语重写（IUR）任务近年来受到广泛关注。其目标是重构对话话语以更好匹配当前语境，从而提升理解效果。本文提出一种新颖且通用的轻量级方法——重写采样多层感知机（RSMLP）。通过基于MLP的架构与精心设计的下采样策略，RSMLP能有效提取话语间的潜在语义信息，并进行合理修正以恢复不完整话语。由于结构简单高效，该方法在公开IUR数据集及真实应用场景中均取得具有竞争力的性能。
原文摘要 · Abstract (English)
The Incomplete Utterance Rewriting (IUR) task has garnered significant attention in recent years. Its goal is to reconstruct conversational utterances to better align with the current context, thereby enhancing comprehension. In this paper, we introduce a novel and versatile lightweight method, Rewritten-Sampled MLP (RSMLP). By employing an MLP based architecture with a carefully designed down-sampling strategy, RSMLP effectively extracts latent semantic information between utterances and makes appropriate edits to restore incomplete utterances. Due to its simple yet efficient structure, our method achieves competitive performance on public IUR datasets and in real-world applications.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。