no code implementations • LREC 2016 • Shih-Ming Wang, Lun-Wei Ku
This paper introduces the augmented NTU sentiment dictionary, abbreviated as ANTUSD, which is constructed by collecting sentiment stats of words in several sentiment annotation work.
no code implementations • 11 Nov 2016 • Wei-Fan Chen, Lun-Wei Ku
Experiments performed on Chinese Facebook data and English online debate forum data show that UTCNN achieves a 0. 755 macro-average f-score for supportive, neutral, and unsupportive stance classes on Facebook data, which is significantly better than models in which either user, topic, or comment information is withheld.
no code implementations • WS 2016 • Wei-Chung Wang, Hung-Chen Chen, Zhi-Kai Ji, Hui-I Hsiao, Yu-Shian Chiu, Lun-Wei Ku
In this work we also introduce two new datasets consisting of 167 phonemic pairs and 279 mixed pairs of aliases and formal names.
no code implementations • COLING 2016 • Wei-Fan Chen, Fang-Yu Lin, Lun-Wei Ku
This paper presents WordForce, a system powered by the state of the art neural network model to visualize the learned user-dependent word embeddings from each post according to the post content and its engaged users.
no code implementations • COLING 2016 • Lun-Wei Ku, Wei-Fan Chen
The basic processing tools are from CKIP Participants can download these resources, use them and solve the problems they encounter in this tutorial.
no code implementations • COLING 2016 • Wei-Fan Chen, Lun-Wei Ku
Experiments performed on Chinese Facebook data and English online debate forum data show that UTCNN achieves a 0. 755 macro average f-score for supportive, neutral, and unsupportive stance classes on Facebook data, which is significantly better than models in which either user, topic, or comment information is withheld.
no code implementations • COLING 2016 • Chieh-Yang Huang, Nicole Peinelt, Lun-Wei Ku
In this paper, we propose GiveMeExample that ranks example sentences according to their capacity of demonstrating the differences among English and Chinese near-synonyms for language learners.
no code implementations • 9 Feb 2017 • Chieh-Yang Huang, Ting-Hao, Huang, Lun-Wei Ku
Instant messaging is one of the major channels of computer mediated communication.
no code implementations • 22 Jul 2017 • Chieh-Yang Huang, Tristan Labetoulle, Ting-Hao Kenneth Huang, Yi-Pei Chen, Hung-Chen Chen, Vallari Srivastava, Lun-Wei Ku
We present MoodSwipe, a soft keyboard that suggests text messages given the user-specified emotions utilizing the real dialog data.
no code implementations • EMNLP 2017 • Chieh-Yang Huang, Tristan Labetoulle, Ting-Hao Huang, Yi-Pei Chen, Hung-Chen Chen, Vallari Srivastava, Lun-Wei Ku
We present MoodSwipe, a soft keyboard that suggests text messages given the user-specified emotions utilizing the real dialog data.
no code implementations • IJCNLP 2017 • Wei-Chung Wang, Lun-Wei Ku
However, most of the lexical inference models with good performance are for nouns or noun phrases, which cannot be directly applied to the inference on events or states.
Natural Language Inference Open-Domain Question Answering +1
no code implementations • IJCNLP 2017 • Szu-Min Chen, Zi-Yuan Chen, Lun-Wei Ku
Categorical sentiment classification has drawn much attention in the field of NLP, while less work has been conducted for dimensional sentiment analysis (DSA).
no code implementations • LREC 2018 • Sheng-Yeh Chen, Chao-Chun Hsu, Chuan-Chun Kuo, Ting-Hao, Huang, Lun-Wei Ku
A total of 29, 245 utterances from 2, 000 dialogues are labeled in EmotionLines.
no code implementations • 30 May 2018 • Chao-Chun Hsu, Szu-Min Chen, Ming-Hsun Hsieh, Lun-Wei Ku
Visual storytelling includes two important parts: coherence between the story and images as well as the story structure.
no code implementations • WS 2018 • Chao-Chun Hsu, Lun-Wei Ku
This paper describes an overview of the Dialogue Emotion Recognition Challenge, EmotionX, at the Sixth SocialNLP Workshop, which recognizes the emotion of each utterance in dialogues.
no code implementations • 6 Mar 2019 • Chao-Chun Hsu, Yu-Hua Chen, Zi-Yuan Chen, Hsin-Yu Lin, Ting-Hao 'Kenneth' Huang, Lun-Wei Ku
In this paper, we introduce Dixit, an interactive visual storytelling system that the user interacts with iteratively to compose a short story for a photo sequence.
no code implementations • NAACL 2019 • Zi-Yuan Chen, Chih-Hung Chang, Yi-Pei Chen, Jijnasa Nayak, Lun-Wei Ku
In relation extraction for knowledge-based question answering, searching from one entity to another entity via a single relation is called "one hop".
no code implementations • WS 2019 • Chieh-Yang Huang, Yi-Ting Huang, Mei-Hua Chen, Lun-Wei Ku
In this study, students learn to differentiate the confusing words by reading the example sentences, and then choose the appropriate word(s) to complete the sentence translation task.
no code implementations • 22 Aug 2019 • Kuan-Yen Lin, Chao-Chun Hsu, Yun-Nung Chen, Lun-Wei Ku
After the entropy-enhanced DMN secures the video context, we apply an attention model that in-corporates summary and caption to generate an accurate answer given the question about the video.
no code implementations • 17 Sep 2019 • Boaz Shmueli, Lun-Wei Ku
We present an overview of the EmotionX 2019 Challenge, held at the 7th International Workshop on Natural Language Processing for Social Media (SocialNLP), in conjunction with IJCAI 2019.
1 code implementation • 3 Dec 2019 • Chao-Chun Hsu, Zi-Yuan Chen, Chi-Yang Hsu, Chih-Chia Li, Tzu-Yuan Lin, Ting-Hao 'Kenneth' Huang, Lun-Wei Ku
This paper introduces KG-Story, a three-stage framework that allows the story generation model to take advantage of external Knowledge Graphs to produce interesting stories.
no code implementations • 17 Jan 2020 • Yun-Wei Chu, Kuan-Yen Lin, Chao-Chun Hsu, Lun-Wei Ku
Understanding dynamic scenes and dialogue contexts in order to converse with users has been challenging for multimodal dialogue systems.
1 code implementation • 6 Feb 2020 • Yun-Zhu Song, Hong-Han Shuai, Sung-Lin Yeh, Yi-Lun Wu, Lun-Wei Ku, Wen-Chih Peng
To generate inspired headlines, we propose a novel framework called POpularity-Reinforced Learning for inspired Headline Generation (PORL-HG).
1 code implementation • 26 May 2020 • Chang-You Tai, Meng-Ru Wu, Yun-Wei Chu, Shao-Yu Chu, Lun-Wei Ku
From the entity view, the mixing layer contrasts layer-wise GCN information to further obtain comprehensive features from internal entity-entity interactions in the KG.
1 code implementation • EMNLP 2020 • Boaz Shmueli, Lun-Wei Ku, Soumya Ray
Sarcasm detection is an important task in affective computing, requiring large amounts of labeled data.
1 code implementation • EMNLP 2020 • Yun-Hsuan Jen, Chieh-Yang Huang, Mei-Hua Chen, Ting-Hao 'Kenneth' Huang, Lun-Wei Ku
The results of the user study show that the proposed agent can find out example sentences that help students learn more easily and efficiently.
no code implementations • 24 Feb 2021 • Boaz Shmueli, Lun-Wei Ku, Soumya Ray
We present an overview of the EmotionGIF2020 Challenge, held at the 8th International Workshop on Natural Language Processing for Social Media (SocialNLP), in conjunction with ACL 2020.
no code implementations • NAACL 2021 • Boaz Shmueli, Jan Fell, Soumya Ray, Lun-Wei Ku
Ethical discussion regarding the use of crowdworkers within the NLP research community is typically confined in scope to issues related to labor conditions such as fair pay.
1 code implementation • Findings (ACL) 2021 • Chi-Yang Hsu, Yun-Wei Chu, Ting-Hao 'Kenneth' Huang, Lun-Wei Ku
Writing a coherent and engaging story is not easy.
Ranked #27 on Visual Storytelling on VIST
1 code implementation • ACL 2021 • Boaz Shmueli, Soumya Ray, Lun-Wei Ku
We show how to augment the data with induced emotion and induced sentiment labels.
no code implementations • ACL 2021 • Chi-Yang Hsu, Yun-Wei Chu, Tsai-Lun Yang, Ting-Hao Huang, Lun-Wei Ku
Therefore, we propose to {``}stretch{''} the stories, which create the potential to present in-depth visual details.
1 code implementation • 16 Dec 2021 • Chang-You Tai, Ming-Yao Li, Lun-Wei Ku
There has been significant progress in utilizing weakly supervised approaches, which require only a small set of seed words for training aspect classifiers.
no code implementations • 19 May 2022 • Shih-Han Chan, Tsai-Lun Yang, Yun-Wei Chu, Chi-Yang Hsu, Ting-Hao Huang, Yu-Shian Chiu, Lun-Wei Ku
An engaging and provocative question can open up a great conversation.
1 code implementation • 10 Jun 2022 • Shih-Chieh Dai, Yi-Li Hsu, Aiping Xiong, Lun-Wei Ku
In this paper, we propose elucidating fact checking predictions using counterfactual explanations to help people understand why a specific piece of news was identified as fake.
1 code implementation • 14 Nov 2022 • Min-Hsuan Yeh, Vicent Chen, Ting-Hao 'Kenneth' Haung, Lun-Wei Ku
These results open up an exciting challenge for visual-and-language models to implicitly construct a story behind a series of photos to allow for creativity and experience sharing and hence draw attention to downstream applications.
1 code implementation • 26 Jun 2023 • Chih-Yao Chen, Tun-Min Hung, Yi-Li Hsu, Lun-Wei Ku
Fine-grained emotion classification (FEC) is a challenging task.
no code implementations • 26 Jun 2023 • Chih-Yao Chen, Dennis Wu, Lun-Wei Ku
Current methods for generating attractive headlines often learn directly from data, which bases attractiveness on the number of user clicks and views.
1 code implementation • 23 Oct 2023 • Nicholas Collin Suwono, Justin Chih-Yao Chen, Tun Min Hung, Ting-Hao Kenneth Huang, I-Bin Liao, Yung-Hui Li, Lun-Wei Ku, Shao-Hua Sun
This work introduces a novel task, location-aware visual question generation (LocaVQG), which aims to generate engaging questions from data relevant to a particular geographical location.
1 code implementation • 23 Oct 2023 • Shih-Chieh Dai, Aiping Xiong, Lun-Wei Ku
Thematic analysis (TA) has been widely used for analyzing qualitative data in many disciplines and fields.
no code implementations • 26 Oct 2023 • Yi-Li Hsu, Shih-Chieh Dai, Aiping Xiong, Lun-Wei Ku
In this study, we compare the effectiveness of a warning label and the state-of-the-art counterfactual explanations generated by GPT-4 in debunking misinformation.
no code implementations • 2 Nov 2023 • Wei-Hsin Yeh, Pei Hsin Lin, Yu-An Su, Wen Hsiang Cheng, Lun-Wei Ku
Many people engage in self-directed sports training at home but lack the real-time guidance of professional coaches, making them susceptible to injuries or the development of incorrect habits.
no code implementations • EMNLP 2021 • Min-Hsuan Yeh, Lun-Wei Ku
Although many studies use the LIWC lexicon to show the existence of verbal leakage cues in lie detection datasets, none mention how verbal leakage cues are influenced by means of data collection, or the impact thereof on the performance of models.
1 code implementation • ACL 2022 • Chi-Yang Hsu, Yun-Wei Chu, Vincent Chen, Kuan-Chieh Lo, Chacha Chen, Ting-Hao Huang, Lun-Wei Ku
In this paper, we present the VHED (VIST Human Evaluation Data) dataset, which first re-purposes human evaluation results for automatic evaluation; hence we develop Vrank (VIST Ranker), a novel reference-free VIST metric for story evaluation.