Heereen Shim
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Heereen Shim has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Bart Vanrumste
Department of Electrical Engineering (ESAT), KU Leuven, 3000 Leuven, Belgium
2 shared publications Dietwig Lowet
Philip Research, Eindhoven, AE, The Netherlands
2 shared publications- Chetanya Puri
E-Media Lab, Campus Groep T, STADIUS, Department of Electrical Engineering, KU Leuven, Leuven, Belgium
1 shared publication - Dominique Lepore
Department of Law, University of Macerata, Macerata, Italy
1 shared publication - Francesca Spigarelli
University of Macerata
1 shared publication - Inhoon Jang
Korea Institute of Industrial Technology
1 shared publication
Latest Publications
- Open Access
- 24 March 2022
- Published by Elsevier in Technovation
- Vol. 120
Interdisciplinary research unlocking innovative solutions in healthcare
- 24 March 2022
- Published by Elsevier in Technovation
- Vol. 120
Open AccessInterdisciplinary research unlocking innovative solutions in healthcare
- Open Access
- 2 August 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 9, 115563-115578
LETS: A Label-Efficient Training Scheme for Aspect-Based Sentiment Analysis by Using a Pre-Trained Language Model
Recently proposed pre-trained language models can be easily fine-tuned to a wide range of downstream tasks. However, a large-scale labelled task-specific dataset is required for fine-tuning creating a bottleneck in the development process of machine learning applications. To foster a fast development by reducing manual labelling efforts, we propose a L abel- E fficient T raining S cheme (LETS). The proposed LETS consists of three elements: (i) task-specific pre-training to exploit unlabelled task-specific corpus data, (ii) label augmentation to maximise the utility of labelled data, and (iii) active learning to label data strategically. In this paper, we apply LETS to a novel aspect-based sentiment analysis (ABSA) use-case for analysing the reviews of the health-related program supporting people to improve their sleep quality. We validate the proposed LETS on a custom health-related program-reviews dataset and another ABSA benchmark dataset. Experimental results show that the LETS can reduce manual labelling efforts 2-3 times compared to labelling with random sampling on both datasets. The LETS also outperforms other state-of-the-art active learning methods. Furthermore, the experimental results show that LETS can contribute to better generalisability with both datasets compared to other methods thanks to the task-specific pre-training and the proposed label augmentation. We expect this work could contribute to the natural language processing (NLP) domain by addressing the issue of the high cost of manually labelling data. Also, our work could contribute to the healthcare domain by introducing a new potential application of NLP techniques.
- 2 August 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 9, 115563-115578
Open AccessLETS: A Label-Efficient Training Scheme for Aspect-Based Sentiment Analysis by Using a Pre-Trained Language Model
Recently proposed pre-trained language models can be easily fine-tuned to a wide range of downstream tasks. However, a large-scale labelled task-specific dataset is required for fine-tuning creating a bottleneck in the development process of machine learning applications. To foster a fast development by reducing manual labelling efforts, we propose a L abel- E fficient T raining S cheme (LETS). The proposed LETS consists of three elements: (i) task-specific pre-training to exploit unlabelled task-specific corpus data, (ii) label augmentation to maximise the utility of labelled data, and (iii) active learning to label data strategically. In this paper, we apply LETS to a novel aspect-based sentiment analysis (ABSA) use-case for analysing the reviews of the health-related program supporting people to improve their sleep quality. We validate the proposed LETS on a custom health-related program-reviews dataset and another ABSA benchmark dataset. Experimental results show that the LETS can reduce manual labelling efforts 2-3 times compared to labelling with random sampling on both datasets. The LETS also outperforms other state-of-the-art active learning methods. Furthermore, the experimental results show that LETS can contribute to better generalisability with both datasets compared to other methods thanks to the task-specific pre-training and the proposed label augmentation. We expect this work could contribute to the natural language processing (NLP) domain by addressing the issue of the high cost of manually labelling data. Also, our work could contribute to the healthcare domain by introducing a new potential application of NLP techniques.
- Open Access
- 1 January 2021
- Published by Association for Computational Linguistics (ACL)
- p. 47-57
Building blocks of a task-oriented dialogue system in the healthcare domain
Heereen Shim, Dietwig Lowet, Stijn Luca, Bart Vanrumste. Proceedings of the Second Workshop on Natural Language Processing for Medical Conversations. 2021.
- 1 January 2021
- Published by Association for Computational Linguistics (ACL)
- p. 47-57
Open AccessBuilding blocks of a task-oriented dialogue system in the healthcare domain
Heereen Shim, Dietwig Lowet, Stijn Luca, Bart Vanrumste. Proceedings of the Second Workshop on Natural Language Processing for Medical Conversations. 2021.
- 1 December 2018
- Published by Elsevier in Cognitive Systems Research
- Vol. 52, 658-667
Multi-tasking deep convolutional network architecture design for extracting nonverbal communicative information from a face
- 1 December 2018
- Published by Elsevier in Cognitive Systems Research
- Vol. 52, 658-667
Multi-tasking deep convolutional network architecture design for extracting nonverbal communicative information from a face