Dialog act is a classification that linguists define according to its function. In order to produce an appropriate response, the dialogue system must be able to distinguish these two intentions effectively. However, users’ questions are expected to be answered, while chatting is expected to interact 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.
.png "chitchat title vidnictus")
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. In recent years, dialogue system is booming and widely used in customer service system, and has achieved good results. The Association for Computational Linguistics and Chinese Language Processing (ACLCLP) Proceedings of the 33rd Conference on Computational Linguistics and Speech Processing (ROCLING 2021) Improve Chit-Chat and QA Sentence Classification in User Messages of Dialogue System using Dialogue Act Embedding
#Chitchat title vidnictus mods
Cite (Informal): Improve Chit-Chat and QA Sentence Classification in User Messages of Dialogue System using Dialogue Act Embedding (Chao et al., ROCLING 2021) Copy Citation: BibTeX Markdown MODS XML Endnote More options… PDF: Data = "Improve Chit-Chat and questions are more related to chat sentences.", The Association for Computational Linguistics and Chinese Language Processing (ACLCLP).
In Proceedings of the 33rd Conference on Computational Linguistics and Speech Processing (ROCLING 2021), pages 138–143, Taoyuan, Taiwan. Improve Chit-Chat and QA Sentence Classification in User Messages of Dialogue System using Dialogue Act Embedding. Anthology ID: 2021.rocling-1.19 Volume: Proceedings of the 33rd Conference on Computational Linguistics and Speech Processing (ROCLING 2021) Month: October Year: 2021 Address: Taoyuan, Taiwan Venue: ROCLING SIG: Publisher: The Association for Computational Linguistics and Chinese Language Processing (ACLCLP) Note: Pages: 138–143 Language: URL: DOI: Bibkey: chao-etal-2021-improve Cite (ACL): Chi Hsiang Chao, Xi Jie Hou, and Yu Ching Chiu. In addition, it is found that conversation behavior types such as “Statement-non-opinion”, “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. The experimental results show that the accuracy of the configuration with dialog act embedding is 16% higher than that with only original statement embedding. Based on the BERT (Bidirectional Encoder Representation from Transformers) model, we build a question-chat classifier model. In this paper, we combine a published COVID-19 QA dataset and a COVID-19-topic chat dataset to form our experimental data. We think this information will help distinguishing questioning sentences and chatting sentences.
Abstract In recent years, dialogue system is booming and widely used in customer service system, and has achieved good results.
0 kommentar(er)
