Markov Logic Networks for Situated Incremental Natural Language Understanding
Markov Logic Networks for Situated Incremental Natural Language Understanding
复制标题
用于情景增量自然语言理解的马尔可夫逻辑网络
DOI：
--
复制
发表时间：
2012
期刊：
影响因子：
--
通讯作者：
David Schlangen
中科院分区：
文献类型：
--
作者：
C. Kennington;David Schlangen
我们介绍了理解自然语言在一个位置领域的工作，即可能是指在视觉上以逐渐逐字的方式呈现的实体。这种类型的理解是需要在语言输入（例如多模式系统或机器人对话系统）上立即起作用的对话系统中的这种理解。我们探索了一组指定为马尔可夫逻辑网络的模型，并表明一个模型可以访问有关话语的视觉上下文，其话语上下文以及话语的语言结构的最佳状态。我们探索其增量属性，以及它在联合解析和理解模块中的使用。我们得出的结论是，MLN提供了一个有希望的框架，用于以一般的，可能与域无关的方式指定此类模型。
We present work on understanding natural language in a situated domain, that is, language that possibly refers to visually present entities, in an incremental, word-by-word fashion. Such type of understanding is required in conversational systems that need to act immediately on language input, such as multi-modal systems or dialogue systems for robots. We explore a set of models specified as Markov Logic Networks, and show that a model that has access to information about the visual context of an utterance, its discourse context, as well as the linguistic structure of the utterance performs best. We explore its incremental properties, and also its use in a joint parsing and understanding module. We conclude that mlns offer a promising framework for specifying such models in a general, possibly domain-independent way.