@inproceedings{jang-etal-2021-bpm,
    title = "{BPM}{\_}{MT}: Enhanced Backchannel Prediction Model using Multi-Task Learning",
    author = "Jang, Jin Yea  and
      Kim, San  and
      Jung, Minyoung  and
      Shin, Saim  and
      Gweon, Gahgene",
    booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2021",
    address = "Online and Punta Cana, Dominican Republic",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2021.emnlp-main.277",
    doi = "10.18653/v1/2021.emnlp-main.277",
    pages = "3447--3452",
    abstract = "Backchannel (BC), a short reaction signal of a listener to a speaker{'}s utterances, helps to improve the quality of the conversation. Several studies have been conducted to predict BC in conversation; however, the utilization of advanced natural language processing techniques using lexical information presented in the utterances of a speaker has been less considered. To address this limitation, we present a BC prediction model called BPM{\_}MT (Backchannel prediction model with multitask learning), which utilizes KoBERT, a pre-trained language model. The BPM{\_}MT simultaneously carries out two tasks at learning: 1) BC category prediction using acoustic and lexical features, and 2) sentiment score prediction based on sentiment cues. BPM{\_}MT exhibited 14.24{\%} performance improvement compared to the existing baseline in the four BC categories: continuer, understanding, empathic response, and No BC. In particular, for empathic response category, a performance improvement of 17.14{\%} was achieved.",
}