Search Results for author: Lun-Wei Ku

Found 43 papers, 11 papers with code

Lying Through One’s Teeth: A Study on Verbal Leakage Cues

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.

Learning to Rank Visual Stories From Human Ranking Data

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.

Learning-To-Rank Visual Storytelling

Multi-VQG: Generating Engaging Questions for Multiple Images

1 code implementation14 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.

Question Answering Question Generation +2

Ask to Know More: Generating Counterfactual Explanations for Fake Claims

1 code implementation10 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.

Counterfactual Explanation Fact Checking +1

Hyperbolic Disentangled Representation for Fine-Grained Aspect Extraction

1 code implementation16 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.

Aspect Extraction

Stretch-VST: Getting Flexible With Visual Stories

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.

Visual Storytelling

Beyond Fair Pay: Ethical Implications of NLP Crowdsourcing

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.

Ethics Misconceptions

SocialNLP EmotionGIF 2020 Challenge Overview: Predicting Reaction GIF Categories on Social Media

no code implementations24 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.

Assessing the Helpfulness of Learning Materials with Inference-Based Learner-Like Agent

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.

Reactive Supervision: A New Method for Collecting Sarcasm Data

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.

Sarcasm Detection

MVIN: Learning Multiview Items for Recommendation

1 code implementation26 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.

Knowledge Graphs Recommendation Systems

Attractive or Faithful? Popularity-Reinforced Learning for Inspired Headline Generation

1 code implementation6 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).

Headline generation

Multi-step Joint-Modality Attention Network for Scene-Aware Dialogue System

no code implementations17 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.

Scene-Aware Dialogue

Knowledge-Enriched Visual Storytelling

1 code implementation3 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.

Knowledge Graphs Story Generation +1

SocialNLP EmotionX 2019 Challenge Overview: Predicting Emotions in Spoken Dialogues and Chats

no code implementations17 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.

Entropy-Enhanced Multimodal Attention Model for Scene-Aware Dialogue Generation

no code implementations22 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.

Dialogue Generation Scene-Aware Dialogue

From Receptive to Productive: Learning to Use Confusing Words through Automatically Selected Example Sentences

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.

Translation

UHop: An Unrestricted-Hop Relation Extraction Framework for Knowledge-Based Question Answering

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".

Question Answering Relation Extraction

Dixit: Interactive Visual Storytelling via Term Manipulation

no code implementations6 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.

Visual Storytelling

SocialNLP 2018 EmotionX Challenge Overview: Recognizing Emotions in Dialogues

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.

Common Sense Reasoning Emotion Recognition

Using Inter-Sentence Diverse Beam Search to Reduce Redundancy in Visual Storytelling

no code implementations30 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.

Visual Storytelling

NLPSA at IJCNLP-2017 Task 2: Imagine Scenario: Leveraging Supportive Images for Dimensional Sentiment Analysis

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).

General Classification Sentiment Analysis

Enabling Transitivity for Lexical Inference on Chinese Verbs Using Probabilistic Soft Logic

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

Challenges in Providing Automatic Affective Feedback in Instant Messaging Applications

no code implementations9 Feb 2017 Chieh-Yang Huang, Ting-Hao, Huang, Lun-Wei Ku

Instant messaging is one of the major channels of computer mediated communication.

Chinese Textual Sentiment Analysis: Datasets, Resources and Tools

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.

Chinese Sentiment Analysis Management +2

UTCNN: a Deep Learning Model of Stance Classification on Social Media Text

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.

Document Classification General Classification +1

WordForce: Visualizing Controversial Words in Debates

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.

Sentiment Analysis Word Embeddings

Automatically Suggesting Example Sentences of Near-Synonyms for Language Learners

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.

UTCNN: a Deep Learning Model of Stance Classificationon on Social Media Text

no code implementations11 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.

Document Classification

ANTUSD: A Large Chinese Sentiment Dictionary

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.

General Classification

Cannot find the paper you are looking for? You can Submit a new open access paper.