no code implementations • ROCLING 2022 • Chin-Tung Lin, Wei-Yun Ma
Most of all, the ancient Chinese corpus is still disappearance in the pre-training stage.
1 code implementation • LREC (LAW) 2022 • Yu-Ming Hsieh, Yueh-Yin Shih, Wei-Yun Ma
This paper describes the conversion of the Sinica Treebank, one of the major Mandarin Chinese treebanks, to Universal Dependencies.
no code implementations • SIGDIAL (ACL) 2020 • Cheng-Hsun Hsueh, Wei-Yun Ma
To address this, in this paper, we propose semantic guidance using reinforcement learning to ensure that the generated responses indeed include the given or predicted semantics and that these semantics do not appear repeatedly in the response.
no code implementations • 8 Mar 2023 • Philipp Ennen, Po-chun Hsu, Chan-Jan Hsu, Chang-Le Liu, Yen-chen Wu, Yin-Hsiang Liao, Chin-Tung Lin, Da-Shan Shiu, Wei-Yun Ma
In this paper we present the multilingual language model BLOOM-zh that features enhanced support for Traditional Chinese.
no code implementations • 13 Dec 2021 • Wei-Lin Liao, Cheng-En Su, Wei-Yun Ma
Recent work on enhancing BERT-based language representation models with knowledge graphs (KGs) and knowledge bases (KBs) has yielded promising results on multiple NLP tasks.
no code implementations • 10 Oct 2021 • Kai-Po Chang, Wei-Yun Ma
In this paper, we propose Dynamic Compressive Transformer (DCT), a transformer-based framework for modeling the unbounded sequence.
1 code implementation • Findings (ACL) 2021 • Jhih-wei Chen, Tsu-Jui Fu, Chen-Kang Lee, Wei-Yun Ma
Experiments on SemEval-2010 and TACRED were conducted with controlled FN ratios that randomly turn the relations of training and validation instances into negatives to generate FN instances.
1 code implementation • 27 Oct 2020 • Hung-Ting Chen, Yu-Chieh Chao, Ta-Hsuan Chao, Wei-Yun Ma
Many neural network models nowadays have achieved promising performances in Chit-chat settings.
no code implementations • LREC 2020 • Mu Yang, Chi-Yen Chen, Yi-Hui Lee, Qian-hui Zeng, Wei-Yun Ma, Chen-Yang Shih, Wei-Jhih Chen
In this paper, we design headword-oriented entity linking (HEL), a specialized entity linking problem in which only the headwords of the entities are to be linked to knowledge bases; mention scopes of the entities do not need to be identified in the problem setting.
no code implementations • 7 Oct 2019 • Peng-Hsuan Li, Tsu-Jui Fu, Wei-Yun Ma
State-of-the-art approaches of NER have used sequence-labeling BiLSTM as a core module.
4 code implementations • 29 Aug 2019 • Peng-Hsuan Li, Tsu-Jui Fu, Wei-Yun Ma
We test the practical impacts of the deficiency on real-world NER datasets, OntoNotes 5. 0 and WNUT 2017, with clear and consistent improvements over the baseline, up to 8. 7% on some of the multi-token entity mentions.
Ranked #17 on Named Entity Recognition (NER) on WNUT 2017
1 code implementation • LREC 2020 • Peng-Hsuan Li, Tsan-Yu Yang, Wei-Yun Ma
We present CA-EHN, the first commonsense word analogy dataset containing 90, 505 analogies covering 5, 656 words and 763 relations.
1 code implementation • ACL 2019 • Tsu-Jui Fu, Peng-Hsuan Li, Wei-Yun Ma
In contrast to previous baselines, we consider the interaction between named entities and relations via a 2nd-phase relation-weighted GCN to better extract relations.
1 code implementation • NAACL 2019 • Hsin-Pei Lee, Jhih-Sheng Fang, Wei-Yun Ma
In this paper, we introduce iComposer, an interactive web-based songwriting system designed to assist human creators by greatly simplifying music production.
1 code implementation • EMNLP 2018 • Tsu-Jui Fu, Wei-Yun Ma
We present LSTM-Shuttle, which applies human speed reading techniques to natural language processing tasks for accurate and efficient comprehension.
no code implementations • IJCNLP 2017 • Peng-Hsuan Li, Wei-Yun Ma, Hsin-Yang Wang
In addition, the CKIP phrase Valence-Arousal (VA) predictor depends on knowledge of modifier words and head words.
no code implementations • IJCNLP 2017 • Yu-Sheng Li, Chien-Hui Tseng, Chian-Yun Huang, Wei-Yun Ma
In this paper, we propose an idea of ondemand knowledge validation and fulfill the idea through an interactive Question-Answering (QA) game system, which is named Guess What.
1 code implementation • EMNLP 2017 • Peng-Hsuan Li, Ruo-Ping Dong, Yu-Siang Wang, Ju-chieh Chou, Wei-Yun Ma
Motivated by the observation that named entities are highly related to linguistic constituents, we propose a constituent-based BRNN-CNN for named entity recognition.
1 code implementation • EACL 2017 • Hsin-Yang Wang, Wei-Yun Ma
Distributional word representations are widely used in NLP tasks.
no code implementations • ROCLINGIJCLCLP 2015 • Chien-Tsung Huang, Yi-Chung Lin, Chao-Chun Liang, Kuang-Yi Hsu, Shen-yun Miao, Wei-Yun Ma, Lun-Wen Ku, Churn-Jung Liau, Keh-Yih Su