French translation of a dialogue dataset and text-based emotion detection

被引：6
作者：
Genest, Pierre-Yves [1 ]
Goix, Laurent-Walter [1 ]
Khalafaoui, Yasser [1 ]
Egyed-Zsigmond, Elod [2 ]
Grozavu, Nistor [3 ]
机构：
[1] ALTECA, 88 Blvd Belges, F-69006 Lyon, France
[2] Univ Lyon, CNRS, UMR 5205, LIRIS, 20 Ave Einstein, F-69621 Villeurbanne, France
[3] CY Cergy Paris Univ, CNRS, UMR 8051, ETIS, 33 Bd Port, F-95000 Cergy, France
来源：
DATA & KNOWLEDGE ENGINEERING | 2022年 / 142卷
关键词：
Affective computing; Classification; Emotion detection; Natural language processing; Methodologies and tools;
D O I：
10.1016/j.datak.2022.102099
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
Chatbots allow computer programs to interact naturally with a user. However, they remain limited due to their lack of sensitivity to the user's state of mind and emotions. This sensitivity will allow the chatbots to provide more accurate answers. Text-based emotion detection has already been explored for the english language (Chatterjee et al., 2019), yet no satisfying french dataset is available. We propose to translate the emotion corpus of multi-party conversation EmotionLines, which is based on the Friends TV show, by exploiting its french broadcasting. Our translation-based dataset generation method is adaptable to any dataset deriving from foreign movies, or TV shows broadcasted in french. Using this translated dataset, we propose a classifier based on BERT, able to detect the user's emotion from text. It takes into account the context of the discussion to improve its inferences.
引用
收藏
页数：18
相关论文
共 38 条
  • [11] Guo CA, 2017, PR MACH LEARN RES, V70
  • [12] Ickes W., 1997, EMPATHY ACCURACY
  • [13] Joulin A, 2016, Arxiv, DOI arXiv:1612.03651
  • [14] Kingma DP, 2014, ADV NEUR IN, V27
  • [15] Le H., 2019, arXiv
  • [16] Li YR, 2017, Arxiv, DOI arXiv:1710.03957
  • [17] Martin L, 2020, Arxiv, DOI arXiv:1911.03894
  • [18] Mikolov T., 2013, P 26 INT C NEURAL IN, V26, DOI 10.5555/2999792.2999959
  • [19] Naeini MP, 2015, AAAI CONF ARTIF INTE, P2901
  • [20] A GENERAL METHOD APPLICABLE TO SEARCH FOR SIMILARITIES IN AMINO ACID SEQUENCE OF 2 PROTEINS
    NEEDLEMAN, SB
    WUNSCH, CD
    [J]. JOURNAL OF MOLECULAR BIOLOGY, 1970, 48 (03) : 443 - +
1234