在信息不全的情况下，让模型学会从对话中推断隐含信息
Decoding Communications with Partial Information
- 基于环境、动作和消息推断缺失信息
- 提出学习算法实现私有信息解码
- 适用于语言学习与通信解析场景
机器语言习得常被视为模仿学习问题：学习者观察语言使用者的言语行为，并试图解码话语与情境之间的映射。然而，一个通常被忽略的关键问题是部分可观测性——即假设学习者能获取所有相关信息。本文放宽这一假设，提出更具挑战性的设定：学习者需根据对环境、已采取动作及发送消息的理解，推断出缺失的信息。文章列举了若干实际应用案例，在简化环境中演示解决方案，并形式化探讨更普遍情形下的挑战。随后提出一种基于学习的算法，用于解码私有信息以支持语言习得。
原文摘要 · Abstract (English)
Machine language acquisition is often presented as a problem of imitation learning: there exists a community of language users from which a learner observes speech acts and attempts to decode the mappings between utterances and situations. However, an interesting consideration that is typically unaddressed is partial observability, i.e. the learner is assumed to see all relevant information. This paper explores relaxing this assumption, thereby posing a more challenging setting where such information needs to be inferred from knowledge of the environment, the actions taken, and messages sent. We see several motivating examples of this problem, demonstrate how they can be solved in a toy setting, and formally explore challenges that arise in more general settings. A learning-based algorithm is then presented to perform the decoding of private information to facilitate language acquisition.
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。