Individuality and Alignment in Generated Dialogues
Individuality and Alignment in Generated Dialogues
复制标题
DOI：
10.3115/1706269.1706277
复制
发表时间：
2006-07
期刊：
影响因子：
--
通讯作者：
Amy Isard;Carsten Brockmann;J. Oberlander
中科院分区：
文献类型：
--
作者：
Amy Isard;Carsten Brockmann;J. Oberlander
使对话代理人能够通过语言手段表现他们的个性或个性将是有益的。同样，一对代理中的每个成员都应该调整自己的语言（或多或少）以匹配其对话者的语言。我们描述了CRAG，它在语言上可区分但能够对齐的代理对之间生成对话。craig -2使用了OPENCCG和一种over-generation和排序方法，由一组涵盖个性和一致性的语言模型指导。我们用输出示例来说明，并简要说明使用早期的CRAG-1进行用户研究的结果，表明如何进一步评估CRAG-2。讨论了相关工作，以及当前的局限性和未来的方向。
It would be useful to enable dialogue agents to project, through linguistic means, their individuality or personality. Equally, each member of a pair of agents ought to adjust its language (to a greater or lesser extent) to match that of its interlocutor. We describe CRAG, which generates dialogues between pairs of agents, who are linguistically distinguishable, but able to align. CRAG-2 makes use of OPENCCG and an over-generation and ranking approach, guided by a set of language models covering both personality and alignment. We illustrate with examples of output, and briefly note results from user studies with the earlier CRAG-1, indicating how CRAG-2 will be further evaluated. Related work is discussed, along with current limitations and future directions.