By attaching a specially designed neural component to dynamically control the impact of linguistic biases in response generation, a Group Linguistic Bias Aware Neural Response Generation (GLBA-NRG) model is eventually presented. To address this issue, this paper proposes to incorporate linguistic biases, which implicitly involved in the conversation corpora generated by human groups in the Social Network Services (SNS), into the encoder-decoder based response generator. Proceedings of the 9th SIGHAN Workshop on Chinese Language ProcessingĪssociation for Computational Linguisticsįor practical chatbots, one of the essential factor for improving user experience is the capability of customizing the talking style of the agents, that is, to make chatbots provide responses meeting users’ preference on language styles, topics, etc. Group Linguistic Bias Aware Neural Response Generation The experimental results on the dataset from the Chinese SNS show that the proposed architecture outperforms the current response generating models by producing both meaningful and vivid responses with customized styles.",
LINGUIST GROUP MODS
Cite (Informal): Group Linguistic Bias Aware Neural Response Generation (Wang et al., 2017) Copy Citation: BibTeX Markdown MODS XML Endnote More options… PDF: = "Group Linguistic Bias Aware Neural Response Generation",īooktitle = "Proceedings of the 9th preference on language styles, topics, etc. Association for Computational Linguistics. In Proceedings of the 9th SIGHAN Workshop on Chinese Language Processing, pages 1–10, Taiwan.
Group Linguistic Bias Aware Neural Response Generation.
| WS SIG: SIGHAN Publisher: Association for Computational Linguistics Note: Pages: 1–10 Language: URL: DOI: Bibkey: wang-etal-2017-group Cite (ACL): Jianan Wang, Xin Wang, Fang Li, Zhen Xu, Zhuoran Wang, and Baoxun Wang. Anthology ID: W17-6001 Volume: Proceedings of the 9th SIGHAN Workshop on Chinese Language Processing Month: December Year: 2017 Address: Taiwan Venues: SIGHAN The experimental results on the dataset from the Chinese SNS show that the proposed architecture outperforms the current response generating models by producing both meaningful and vivid responses with customized styles.
Abstract For practical chatbots, one of the essential factor for improving user experience is the capability of customizing the talking style of the agents, that is, to make chatbots provide responses meeting users’ preference on language styles, topics, etc.
0 kommentar(er)
