arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2006.07015cs.CL
收藏

说话人敏感反应评价模型

Speaker Sensitive Response Evaluation Model

KAIST(韩国科学技术院)

JinYeong Bak, Alice Oh

摘要:

开放域对话响应生成的自动评估是非常具有挑战性的,因为对于给定的上下文有许多适当的响应。现有的评估模型只是将生成的响应与地面实况响应进行比较,并且如果它们偏离地面实况,则将许多适当的响应评定为不适当的。解决这个问题的一种方法是考虑所生成的响应与会话上下文的相似性。本文提出了一个基于该思想的自动评价模型,并从一个未标注的会话语料库中学习模型参数。我们的方法认为,在定义不同层次的类似的情况下,扬声器。我们使用一个Twitter的会话语料库,其中包含许多扬声器和对话来测试我们的评估模型。实验表明,我们的模型优于其他现有的评价指标,与人类注释分数的高度相关性。我们还表明,我们在Twitter上训练的模型可以应用于电影对话,而无需任何额外的训练。我们提供了我们的代码和学习的参数,以便它们可以用于对话响应生成模型的自动评估。

英文摘要:

Automatic evaluation of open-domain dialogue response generation is very challenging because there are many appropriate responses for a given context. Existing evaluation models merely compare the generated response with the ground truth response and rate many of the appropriate responses as inappropriate if they deviate from the ground truth. One approach to resolve this problem is to consider the similarity of the generated response with the conversational context. In this paper, we propose an automatic evaluation model based on that idea and learn the model parameters from an unlabeled conversation corpus. Our approach considers the speakers in defining the different levels of similar context. We use a Twitter conversation corpus that contains many speakers and conversations to test our evaluation model. Experiments show that our model outperforms the other existing evaluation metrics in terms of high correlation with human annotation scores. We also show that our model trained on Twitter can be applied to movie dialogues without any additional training. We provide our code and the learned parameters so that they can be used for automatic evaluation of dialogue response generation models.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑