Web API recommendations have recently been studied extensively. However, recommending an API for a service is different than service intelligence. Web API automatic calls are widely used in question–answer dialog applications and service-composed workflow systems to achieve intelligent services. To finish an automatic Web API call not only requires the Web API ID, but also its input parameters. In this paper, we propose an end-to-end Web API automatic calls approach, named WAAC, that translates a goal’s natural language sentences directly to the Web API invoking sequences including its ID and parameters. This end-to-end approach based on the seq2seq encoder–decoder framework, adopts character-level RNN for the Chinese sentences and introduces a copying mechanism to retrieve API parameters. To train the network, a Chinese version dataset of over 1 million natural sentences and API invoking sequence pairs are generated with some manually labeled data and 72 real Web API invoking logs. Experiments obtain a 96% precision on predicting API invoking sequences and show that the character-level RNN and copying mechanism both contribute considerably to achieving a high precision Web API automatic call system for goal-oriented services.

中文翻译：

---

WAAC：面向目标的智能服务的端到端 Web API 自动调用方法

Web API 建议最近得到了广泛的研究。但是，为服务推荐 API 与服务智能不同。Web API 自动调用广泛应用于问答对话应用和服务组合工作流系统，以实现智能服务。要完成自动 Web API 调用，不仅需要 Web API ID，还需要其输入参数。在本文中，我们提出了一种名为 WAAC 的端到端 Web API 自动调用方法，该方法将目标的自然语言句子直接翻译为 Web API 调用序列，包括其 ID 和参数。这种基于 seq2seq 编码器-解码器框架的端到端方法，对中文句子采用字符级 RNN，并引入了复制机制来检索 API 参数。为了训练网络，使用人工标注的数据和72条真实的Web API调用日志，生成超过100万自然句和API调用序列对的中文版数据集。实验在预测 API 调用序列方面获得了 96% 的精度，并表明字符级 RNN 和复制机制都有助于实现面向目标服务的高精度 Web API 自动调用系统。