1 code implementation • NLP4IF (COLING) 2020 • Timothy Niven, Hung-Yu Kao
We introduce what is to the best of our knowledge a new task in natural language processing: measuring alignment to authoritarian state media.
no code implementations • 20 Feb 2024 • Ying-Jia Lin, Chun-Yi Lin, Chia-Jen Yeh, Yi-Ting Li, Yun-Yu Hu, Chih-Hao Hsu, Mei-Feng Lee, Hung-Yu Kao
Similar to the FEVER dataset, claims in the "Supports" and "Refutes" categories are also annotated with corresponding evidence sentences sourced from single or multiple pages in Chinese Wikipedia.
1 code implementation • 17 Jul 2022 • Shiwen Ni, Hung-Yu Kao
Numerically, compared to MLM-RoBERTa-large and MLM-BERT-large, our RTD-ELECTRA-large has an average of about 8. 4% and 13. 7% improvement on all 15 tasks.
no code implementations • 1 Dec 2021 • Shiwen Ni, Jiawen Li, Hung-Yu Kao
It is difficult for humans to distinguish the true and false of rumors, but current deep learning models can surpass humans and achieve excellent accuracy on many rumor datasets.
1 code implementation • 29 Aug 2021 • Shiwen Ni, Jiawen Li, Hung-Yu Kao
We compare the proposed method with other adversarial training methods and regularization methods, and our method achieves state-of-the-art on all datasets.
no code implementations • 29 Aug 2021 • Shiwen Ni, Jiawen Li, Hung-Yu Kao
As such, the robustness and generalization of the current rumor detection model are put into question.
1 code implementation • ACL 2021 • Reinald Adrian Pugoy, Hung-Yu Kao
Our explainability study demonstrates the superiority of and preference for summary-level explanations over other explanation types.
no code implementations • Asian Chapter of the Association for Computational Linguistics 2020 • Reinald Adrian Pugoy, Hung-Yu Kao
First is their utilization of traditional word embeddings that could influence prediction performance due to their inability to model the word semantics{'} dynamic characteristic.
no code implementations • COLING 2020 • Jiawen Li, Yudianto Sujana, Hung-Yu Kao
Twitter users communicate by replying to other users{'} messages, forming a conversation structure.
no code implementations • Asian Chapter of the Association for Computational Linguistics 2020 • Yudianto Sujana, Jiawen Li, Hung-Yu Kao
Inspired by the hierarchical model and multitask learning, a multiloss hierarchical BiLSTM model with an attenuation factor is proposed in this paper.
1 code implementation • WS 2019 • Kai-Chou Yang, Timothy Niven, Tzu Hsuan Chou, Hung-Yu Kao
In this paper, we describe our entry in the gendered pronoun resolution competition which achieved fourth place without data augmentation.
1 code implementation • WS 2019 • Timothy Niven, Hung-Yu Kao
We report the results of preliminary investigations into the relationship between linguistic alignment and dialogical argumentation at the level of discourse acts.
1 code implementation • 17 Jul 2019 • Kai-Chou Yang, Timothy Niven, Hung-Yu Kao
The remainder of test cases are classified by our ensemble.
Ranked #1 on Concept-To-Text Generation on COCO Captions
1 code implementation • ACL 2019 • Timothy Niven, Hung-Yu Kao
We are surprised to find that BERT's peak performance of 77% on the Argument Reasoning Comprehension Task reaches just three points below the average untrained human baseline.
no code implementations • 27 Nov 2018 • TonTon Hsien-De Huang, Po-Wei Hong, Ying-Tse Lee, Yi-Lun Wang, Chi-Leong Lok, Hung-Yu Kao
Ethereum is gaining a significant popularity in blockchain community, mainly due to the fact that it is designed in a way that enables developers to write smart contracts and decentralized applications (Dapps).
1 code implementation • SEMEVAL 2018 • Tim Niven, Hung-Yu Kao
Encoder transfer yields a significant gain to our best model over random initialization.
no code implementations • SEMEVAL 2017 • Yi-Chin Chen, Zhao-Yang Liu, Hung-Yu Kao
This paper describes our approach for SemEval-2017 Task 8.
no code implementations • 12 May 2017 • TonTon Hsien-De Huang, Hung-Yu Kao
The color image is input to the convolutional neural network for automatic feature extraction and training.