Spoken Dialogue Management Using Probabilistic Reasoning
Spoken Dialogue Management Using Probabilistic Reasoning
复制标题
DOI：
10.3115/1075218.1075231
复制
发表时间：
2000-10
期刊：
影响因子：
--
通讯作者：
N. Roy;Joelle Pineau;S. Thrun
中科院分区：
文献类型：
--
作者：
N. Roy;Joelle Pineau;S. Thrun
口语对话管理者从使用随机规划器（例如马尔可夫决策过程（MDP））中受益匪浅。然而，到目前为止，MDP不能很好地处理嘈杂和模糊的语音话语。我们使用部分可观察马尔可夫决策过程（POMDP）风格的方法来生成对话策略，通过反转对话状态的概念;状态代表用户的意图，而不是系统状态。我们证明，在相同的嘈杂条件下，POMDP对话管理器比MDP对话管理器的错误少。此外，随着语音识别质量的下降，POMDP对话管理器自动调整策略。
Spoken dialogue managers have benefited from using stochastic planners such as Markov Decision Processes (MDPs). However, so far, MDPs do not handle well noisy and ambiguous speech utterances. We use a Partially Observable Markov Decision Process (POMDP)-style approach to generate dialogue strategies by inverting the notion of dialogue state; the state represents the user's intentions, rather than the system state. We demonstrate that under the same noisy conditions, a POMDP dialogue manager makes fewer mistakes than an MDP dialogue manager. Furthermore, as the quality of speech recognition degrades, the POMDP dialogue manager automatically adjusts the policy.