支援訓練語句分析與擴增之Web API對話機器人生成機制

Web-API-Based Chatbot Generation with Analysis and Expansion for Training Sentences

對話機器人(Chatbot)是近年來受到廣泛歡迎的新穎技術，在Web API技術日趨成熟的趨勢下，如何結合Web API與Chatbot技術也開始成為備受關注的議題。本研究規劃建立一個可基於Web API生成Chatbot之半自動化方法BOTEN及其實作平台，透過此方法，可協助應用程式開發者快速建置出指定Web API的Chatbot介面。為了確保Chatbot具備足夠的自然語言理解(Natural Language Understanding, NLU)能力，本研究透過TF-IDF、WordNet與SpaCy技術評估開發者撰寫的訓練語句，對品質不佳的訓練語句提出警訊，以提供訓練語句修改之建議；此外，本研究亦提出一個自動擴增訓練語句數量之方法，以進一步提升Chatbot的意圖辨識能力。

With Web API technology becoming increasingly mature, how to integrate Web API and Chatbot technology has become an issue of great interest. This study plans to build a semi-automatic method and tool, BOTEN. This method allows application developers to build Chatbot interfaces with specified Web APIs quickly. To ensure that the Chatbot has sufficient natural language understanding (NLU) capability, this research evaluates the training sentences written by the developer through TF-IDF, WordNet, and SpaCy techniques, and suggests the developer modify the training sentences with poor quality. This technique can also be used to automatically increase the number of training sentences to improve the capability of Intent recognition.