Affective Prompt-Tuning-Based Language Model for Semantic-Based Emotional Text Generation
Authors:
Open Access
- 1 January 2024
- journal article
- research article
- Published by IGI Global Scientific Publishing in International Journal on Semantic Web and Information Systems
- Vol. 20 (1) , 1-19
Abstract
The large language models based on transformers have shown strong text generation ability. However, due to the need for significant computing resources, little work has been done to generate emotional text using language models such as GPT-2. To address this issue, the authors proposed an affective prompt-tuning-based language model (APT-LM) equipped with an affective decoding (AD) method, aiming to enhance emotional text generation with limited computing resources. In detail, the proposed model incorporates the emotional attributes into the soft prompt by using the NRC emotion intensity lexicon and updates the additional parameters while freezing the language model. Then, it steers the generation toward a given emotion by calculating the cosine distance between the affective soft prompt and the candidate tokens generated by the language model. Experimental results show that the proposed APT-LM model significantly improves emotional text generation and achieves competitive performance on sentence fluency compared to baseline models across automatic evaluation and human evaluation.Keywords
This publication has 37 references indexed in Scilit:
- Evaluation of Cooperative Intelligent Transportation System scenarios for resilience in transportation using type-2 neutrosophic fuzzy VIKORTransportation Research Part A: Policy and Practice, 2023
- A Deep Learning-based Fast Fake News Detection Model for Cyber-Physical Social ServicesPattern Recognition Letters, 2023
- Exploring the effect of digital transformation on Firms’ innovation performanceJournal of Innovation & Knowledge, 2023
- Analysis of artificial intelligence-based technologies and approaches on sustainable entrepreneurshipTechnological Forecasting and Social Change, 2022
- Numerical solution of systems of second-order boundary value problems using continuous genetic algorithmInformation Sciences, 2014
- THE EMPATHIC COMPANION: A CHARACTER-BASED INTERFACE THAT ADDRESSES USERS' AFFECTIVE STATESApplied Artificial Intelligence, 2005
- Core affect and the psychological construction of emotion.Psychological Review, 2003
- Evidence for universality and cultural variation of differential emotion response patterning.Journal of Personality and Social Psychology, 1994
- Is there universal recognition of emotion from facial expression? A review of the cross-cultural studies.Psychological Bulletin, 1994
- An argument for basic emotionsCognition and Emotion, 1992