Affect-LM: A Neural Language Model for Customizable Affective Text Generation

被引:84
|
作者
Ghosh, Sayan [1 ]
Chollet, Mathieu [1 ]
Laksana, Eugene [1 ]
Morency, Louis-Philippe [2 ]
Scherer, Stefan [1 ]
机构
[1] Univ Southern Calif, Inst Creat Technol, Los Angeles, CA 90007 USA
[2] Carnegie Mellon Univ, Language Technol Inst, Pittsburgh, PA 15213 USA
关键词
D O I
10.18653/v1/P17-1059
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
Human verbal communication includes affective messages which are conveyed through use of emotionally colored words. There has been a lot of research in this direction but the problem of integrating state-of-the-art neural language models with affective information remains an area ripe for exploration. In this paper, we propose an extension to an LSTM (Long Short-Term Memory) language model for generating conversational text, conditioned on affect categories. Our proposed model, Affect-LM enables us to customize the degree of emotional content in generated sentences through an additional design parameter. Perception studies conducted using Amazon Mechanical Turk show that Affect-LM generates naturally looking emotional sentences without sacrificing grammatical correctness. Affect-LM also learns affect-discriminative word representations, and perplexity experiments show that additional affective information in conversational text can improve language model prediction.
引用
收藏
页码:634 / 642
页数:9
相关论文
共 44 条
  • [1] Neural Data-to-Text Generation with LM-based Text Augmentation
    Chang, Ernie
    Shen, Xiaoyu
    Zhu, Dawei
    Demberg, Vera
    Su, Hui
    [J]. 16TH CONFERENCE OF THE EUROPEAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (EACL 2021), 2021, : 758 - 768
  • [2] Exploring Language Diversity to Improve Neural Text Generation
    Xu, Lingjiao
    Chen, Xingyuan
    Wang, Bing
    Jin, Peng
    [J]. KNOWLEDGE SCIENCE, ENGINEERING AND MANAGEMENT, PT V, KSEM 2024, 2024, 14888 : 245 - 254
  • [3] Affective Prompt-Tuning-Based Language Model for Semantic-Based Emotional Text Generation
    Gu, Zhaodong
    He, Kejing
    [J]. INTERNATIONAL JOURNAL ON SEMANTIC WEB AND INFORMATION SYSTEMS, 2024, 20 (01)
  • [4] COCO-LM: Correcting and Contrasting Text Sequences for Language Model Pretraining
    Meng, Yu
    Xiong, Chenyan
    Bajaj, Payal
    Tiwary, Saurabh
    Bennett, Paul
    Han, Jiawei
    Song, Xia
    [J]. ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 34 (NEURIPS 2021), 2021, 34
  • [5] SSD-LM: Semi-autoregressive Simplex-based Diffusion Language Model for Text Generation and Modular Control
    Han, Xiaochuang
    Kumar, Sachin
    Tsvetkov, Yulia
    [J]. PROCEEDINGS OF THE 61ST ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2023): LONG PAPERS, VOL 1, 2023, : 11575 - 11596
  • [6] Stochastic Tokenization with a Language Model for Neural Text Classification
    Hiraoka, Tatsuya
    Shindo, Hiroyuki
    Matsumoto, Yuji
    [J]. 57TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2019), 2019, : 1620 - 1629
  • [7] Text generation by probabilistic suffix tree language model
    Marukatat, Sanparith
    [J]. 16TH INTERNATIONAL JOINT SYMPOSIUM ON ARTIFICIAL INTELLIGENCE AND NATURAL LANGUAGE PROCESSING (ISAI-NLP 2021), 2021,
  • [8] Text-Guided Molecule Generation with Diffusion Language Model
    Gong, Haisong
    Liu, Qiang
    Wu, Shu
    Wang, Liang
    [J]. THIRTY-EIGHTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL 38 NO 1, 2024, : 109 - 117
  • [9] Social Media Text Generation Based on Neural Network Model
    Cao, Jiarun
    Wang, Chongwen
    [J]. PROCEEDINGS OF 2018 THE 2ND INTERNATIONAL CONFERENCE ON COMPUTER SCIENCE AND ARTIFICIAL INTELLIGENCE (CSAI 2018) / 2018 THE 10TH INTERNATIONAL CONFERENCE ON INFORMATION AND MULTIMEDIA TECHNOLOGY (ICIMT 2018), 2018, : 58 - 61
  • [10] Learning to Diversify Neural Text Generation via Degenerative Model
    Hong, Jimin
    Park, ChaeHun
    Choo, Jaegul
    [J]. 13TH INTERNATIONAL JOINT CONFERENCE ON NATURAL LANGUAGE PROCESSING AND THE 3RD CONFERENCE OF THE ASIA-PACIFIC CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, IJCNLP-AACL 2023, 2023, : 55 - 64