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 2005.00036cs.CL
收藏

提高响应和人物角色事实之间的事实一致性

Improving Factual Consistency Between a Response and Persona Facts

Technical University of Darmstadt(达姆施塔特工业大学);University of Bristol(布里斯托尔大学)

Mohsen Mesgar, Edwin Simpson, Iryna Gurevych

摘要:

用于响应生成的神经模型产生的响应在语义上是合理的,但不一定与描述说话者角色的事实一致。这些模型是用完全监督学习训练的,其中目标函数几乎不能捕捉事实的一致性。我们建议通过强化学习和一个有效的奖励函数来微调这些模型,该函数显式地捕获响应和人物角色事实之间的一致性以及语义可扩展性。我们对PersonaChat语料库的自动和人工评估证实,我们的方法增加了与其监督对应物实际上与人物角色事实一致的响应率,同时保留了响应的语言质量。

英文摘要:

Neural models for response generation produce responses that are semantically plausible but not necessarily factually consistent with facts describing the speaker's persona. These models are trained with fully supervised learning where the objective function barely captures factual consistency. We propose to fine-tune these models by reinforcement learning and an efficient reward function that explicitly captures the consistency between a response and persona facts as well as semantic plausibility. Our automatic and human evaluations on the PersonaChat corpus confirm that our approach increases the rate of responses that are factually consistent with persona facts over its supervised counterpart while retaining the language quality of responses.

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。

↑