Haw-Shiuan Chang
Haw-Shiuan Chang
Verified email at - Homepage
Cited by
Cited by
Active bias: Training more accurate neural networks by emphasizing high variance samples
HS Chang, E Learned-Miller, A McCallum
Advances in Neural Information Processing Systems 30, 2017
Inorganic materials synthesis planning with literature-trained neural networks
E Kim, Z Jensen, A van Grootel, K Huang, M Staib, S Mysore, HS Chang, ...
Journal of chemical information and modeling 60 (3), 1194-1201, 2020
The materials science procedural text corpus: Annotating materials synthesis procedures with shallow semantic structures
S Mysore, Z Jensen, E Kim, K Huang, HS Chang, E Strubell, J Flanigan, ...
arXiv preprint arXiv:1905.06939, 2019
Autoknow: Self-driving knowledge collection for products of thousands of types
XL Dong, X He, A Kan, X Li, Y Liang, J Ma, YE Xu, C Zhang, T Zhao, ...
Proceedings of the 26th ACM SIGKDD International Conference on Knowledge …, 2020
Exploring visual and motion saliency for automatic video object extraction
WT Li, HS Chang, KC Lien, HT Chang, YCF Wang
IEEE Transactions on Image Processing 22 (7), 2600-2610, 2013
Modeling Exercise Relationships in E-Learning: A Unified Approach
HS Chang, HJ Hsu, KT Chen
International Conference on Educational Data Mining (EDM), 2015
Distributional Inclusion Vector Embedding for Unsupervised Hypernymy Detection
HS Chang, ZY Wang, L Vilnis, A McCallum
Proceedings of the 2018 Conference of the North American Chapter of the …, 2018
Open aspect target sentiment classification with natural language prompts
R Seoh, I Birle, M Tak, HS Chang, B Pinette, A Hough
arXiv preprint arXiv:2109.03685, 2021
Automatically extracting action graphs from materials science synthesis procedures
S Mysore, E Kim, E Strubell, A Liu, HS Chang, S Kompella, K Huang, ...
arXiv preprint arXiv:1711.06872, 2017
Active learning for crowdsourced QoE modeling
HS Chang, CF Hsu, T Hoßfeld, KT Chen
IEEE Transactions on Multimedia 20 (12), 3337-3352, 2018
Optimizing the decomposition for multiple foreground cosegmentation
HS Chang, YCF Wang
Computer Vision and Image Understanding 141, 18-27, 2015
Using error decay prediction to overcome practical issues of deep active learning for named entity recognition
HS Chang, S Vembu, S Mohan, R Uppaal, A McCallum
Machine Learning 109, 1749-1778, 2020
Superpixel-based large displacement optical flow
HS Chang, YCF Wang
2013 IEEE international conference on image processing, 3835-3839, 2013
Changing the mind of transformers for topically-controllable language generation
HS Chang, J Yuan, M Iyyer, A McCallum
arXiv preprint arXiv:2103.15335, 2021
Softmax bottleneck makes language models unable to represent multi-mode word distributions
HS Chang, A McCallum
Proceedings of the 60th Annual Meeting of the Association for Computational …, 2022
Extending multi-sense word embedding to phrases and sentences for unsupervised semantic applications
HS Chang, A Agrawal, A McCallum
Proceedings of the AAAI Conference on Artificial Intelligence 35 (8), 6956-6965, 2021
Efficient graph-based word sense induction by distributional inclusion vector embeddings
HS Chang, A Agrawal, A Ganesh, A Desai, V Mathur, A Hough, ...
arXiv preprint arXiv:1804.03257, 2018
Extracting Multilingual Relations under Limited Resources: TAC 2016 Cold-Start KB construction and Slot-Filling using Compositional Universal Schema.
HS Chang, A Munir, A Liu, JTZ Wei, A Traylor, A Nagesh, N Monath, ...
TAC, 2016
Revisiting the architectures like pointer networks to efficiently improve the next word distribution, summarization factuality, and beyond
HS Chang, Z Yao, A Gon, H Yu, A McCallum
arXiv preprint arXiv:2305.12289, 2023
Multi-CLS BERT: An efficient alternative to traditional ensembling
HS Chang, RY Sun, K Ricci, A McCallum
arXiv preprint arXiv:2210.05043, 2022
The system can't perform the operation now. Try again later.
Articles 1–20