781 citations
- National Taiwan UniversityTW50 papers
- National Tsing Hua UniversityTW25 papers
- Academia SinicaTW15 papers
- National Taipei UniversityTW14 papers
- National Center for Theoretical SciencesTW13 papers
- National Yang Ming Chiao Tung UniversityTW8 papers
- Research Center for Information Technology Innovation, Academia SinicaTW8 papers
- University of MichiganUS8 papers
- Syracuse UniversityUS7 papers
- Centre National de la Recherche ScientifiqueFR6 papers
- Institute of Information Science, Academia SinicaTW6 papers
- Eindhoven University of TechnologyNL5 papers
9 papers · 1 filter
Leveraging Large Language Models for Entity Matching
Qianyu Huang, Tongfang Zhao
Entity matching (EM) is a critical task in data integration, aiming to identify records across different datasets that refer to the same real-world entities. Traditional methods of…
Large Language Model Pruning
Hanjuan Huang, Hao-Jia Song, Hsing-Kuo Pao
We surely enjoy the larger the better models for their superior performance in the last couple of years when both the hardware and software support the birth of such extremely huge…
Rating Facts under Coarse-to-fine Regimes
Guojun Wu
The rise of manipulating fake news as a political weapon has become a global concern and highlighted the incapability of manually fact checking against rapidly produced fake news.…
Non-autoregressive Transformer-based End-to-end ASR using BERT
Fu-Hao Yu, Kuan-Yu Chen
Transformer-based models have led to significant innovation in classical and practical subjects as varied as speech processing, natural language processing, and computer vision. On…
An Audio-enriched BERT-based Framework for Spoken Multiple-choice Question Answering
Chia-Chih Kuo, Shang-Bao Luo, Kuan-Yu Chen
In a spoken multiple-choice question answering (SMCQA) task, given a passage, a question, and multiple choices all in the form of speech, the machine needs to pick the correct choi…
A neural document language modeling framework for spoken document retrieval
Li-Phen Yen, Zhen-Yu Wu, Kuan-Yu Chen
Recent developments in deep learning have led to a significant innovation in various classic and practical subjects, including speech recognition, computer vision, question answeri…