With the rapid development of artificial intelligence, conversational bots have became prevalent in mainstream E-commerce platforms, which can provide convenient customer service timely. To satisfy the user, the conversational bots need to understand the user's intention, detect the user's emotion, and extract the key entities from the conversational utterances. However, understanding dialogues is regarded as a very challenging task. Different from common language understanding, utterances in dialogues appear alternately from different roles and are usually organized as hierarchical structures. To facilitate the understanding of dialogues, in this paper, we propose a novel contextual dialogue encoder (i.e. DialogueBERT) based on the popular pre-trained language model BERT. Five self-supervised learning pre-training tasks are devised for learning the particularity of dialouge utterances. Four different input embeddings are integrated to catch the relationship between utterances, including turn embedding, role embedding, token embedding and position embedding. DialogueBERT was pre-trained with 70 million dialogues in real scenario, and then fine-tuned in three different downstream dialogue understanding tasks. Experimental results show that DialogueBERT achieves exciting results with 88.63% accuracy for intent recognition, 94.25% accuracy for emotion recognition and 97.04% F1 score for named entity recognition, which outperforms several strong baselines by a large margin.
翻译:随着人工智能的迅速发展,对话机器人在主流电子商务平台中变得十分普遍,能够及时提供方便的客户服务。满足用户的需要,对话机器人需要理解用户的意图,检测用户的情感,并从谈话语句中提取关键实体。然而,理解对话被视为一项非常具有挑战性的任务。与共同语言理解不同,对话中的言论似乎与不同角色交替不同,通常组织为等级结构。为了便利对对话的理解,在本文件中,我们提议以受欢迎的预先培训的语言模式BERT为基础,建立新的背景对话编码器(即对话BERT)。设计了五个自我监督的学习前培训任务,以学习拨号语句的特殊性。四种不同的输入嵌入是结合到语音之间的关系,包括转换嵌入、角色嵌入、象征性嵌入和嵌入等。为了真实情景,我们预先培训了7 000万次对话,然后对三种不同的下游对话理解空间任务进行了精确度调整。 实验结果显示,95 %的学习前精确度,通过测试结果显示88的精确度,使实体确认达到一定的精确度。