使用對話行為嵌入改善對話系統用戶訊息中提問句與閒聊句之判別

Improve Chit-Chat and QA Sentence Classification in User Messages of Dialogue System using Dialogue Act Embedding

近年來，對話系統蓬勃發展並被廣泛應用於客服系統並取得了不錯的成效。檢視用戶與真人客服間的對話紀錄，可以發覺用戶的語句夾雜著對產品與服務的問題，以及和客服之間的閒聊。根據專業人員的經驗，在客服對話中適當地夾雜閒聊有助於提升用戶的體驗。然而，用戶提問是期望獲得解答，閒聊則是期望與客服有人與人之間的互動交流。面對這兩種意圖，對話系統必須能有效判別，已產生適當的回應。對話行為(Dialog Act)是語言學家將對話語句依據其作用定義出的一種分類方式。我們認為這個資訊將有助於集問句及閒聊句的區分。在本研究中，我們結合一個已公開的Covid-19問答集及一個Covid-19主題的閒聊資料集組成我們的實驗資料。我們基於BERT (Bidirectional EncoderRepresentation from Transformers)模型建立了一個提問句—閒聊句分類器模型。實驗結果顯示，加入對話行為嵌入(Dialog ActEmbedding)的組態比僅使用原始語句嵌入的組態準確率高了16%。此外，經過分析發現，Statement-non-opinion、Signal-nonunderstanding、Appreciation等對話行為類型與提問句較相關，Wh-Question、Yes-No-Question、Rhetorical-Question等類型則與閒聊句較相關。

In recent years, dialogue system is booming and widely used in customer service system, and has achieved good results. Viewing the conversation records between users and real customer service, we can see that the user's sentences are mixed with questions about products and services, and chat with customer service. According to the experience of professionals, it is helpful in improving the user experience to mix some chats in customer service conversations. However, users' questions are expected to be answered, while chatting is expected to interact with customer service. In order to produce an appropriate response, the dialogue system must be able to distinguish these two intentions effectively. Dialog act is a classification that linguists define according to its function. We think this information will help distinguishing questioning sentences and chatting sentences. In this paper, we combine a published COVID-19 QA dataset and a COVID-19-topic chat dataset to form our experimental data. Based on the BERT (Bidirectional Encoder Representation from Transformers) model, we build a question-chat classifier model. The experimental results show that the accuracy of the configuration with dialog act embedding is 16% higher than that with only original statement embedding. In addition, it is found that conversation behavior types such as 'Statement-nonopinion', 'Signal-non-understanding' and 'Appreciation' are more related to question sentences, while 'Wh-Question', 'Yes-No-Question' and 'Rhetorical-Question' questions are more related to chat sentences.