arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2109.05487cs.CL
收藏

用于在对话生成中更好地处理不可见实体的知识增强微调

Knowledge Enhanced Fine-Tuning for Better Handling Unseen Entities in Dialogue Generation

Microsoft Research Asia(微软亚洲研究院);Westlake University(西湖大学);Zhejiang University(浙江大学)

Leyang Cui, Yu Wu, Shujie Liu, Yue Zhang

摘要:

虽然预训练模型在对话生成方面取得了巨大的成功,但当输入包含未出现在预训练和微调数据集中的实体(未见过的实体)时,它们的性能会急剧下降。为了解决这个问题,现有的方法利用外部知识库来生成适当的响应。在现实世界中,实体可能不包括在知识库中,或者受到知识检索精度的影响。为了解决这个问题,我们不引入知识库作为输入,而是通过预测知识库中的信息,仅基于输入上下文,迫使模型学习更好的语义表示。具体地说,在知识库的帮助下,我们引入了两个辅助训练目标:1)解释屏蔽词,它在给定上下文的情况下解释屏蔽实体的含义; 2)上位词生成,它根据上下文预测实体的上位词。在两个对话语料库上的实验结果验证了该方法在知识可用和不可用两种情况下的有效性。

英文摘要:

Although pre-training models have achieved great success in dialogue generation, their performance drops dramatically when the input contains an entity that does not appear in pre-training and fine-tuning datasets (unseen entity). To address this issue, existing methods leverage an external knowledge base to generate appropriate responses. In real-world scenario, the entity may not be included by the knowledge base or suffer from the precision of knowledge retrieval. To deal with this problem, instead of introducing knowledge base as the input, we force the model to learn a better semantic representation by predicting the information in the knowledge base, only based on the input context. Specifically, with the help of a knowledge base, we introduce two auxiliary training objectives: 1) Interpret Masked Word, which conjectures the meaning of the masked entity given the context; 2) Hypernym Generation, which predicts the hypernym of the entity based on the context. Experiment results on two dialogue corpus verify the effectiveness of our methods under both knowledge available and unavailable settings.

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。

↑