Hung-Yu Kao


2020

pdf bib
Measuring Alignment to Authoritarian State Media as Framing Bias
Timothy Niven | Hung-Yu Kao
Proceedings of the 3rd NLP4IF Workshop on NLP for Internet Freedom: Censorship, Disinformation, and Propaganda

We introduce what is to the best of our knowledge a new task in natural language processing: measuring alignment to authoritarian state media. We operationalize alignment in terms of sociological definitions of media bias. We take as a case study the alignment of four Taiwanese media outlets to the Chinese Communist Party state media. We present the results of an initial investigation using the frequency of words in psychologically meaningful categories. Our findings suggest that the chosen word categories correlate with framing choices. We develop a calculation method that yields reasonable results for measuring alignment, agreeing well with the known labels. We confirm that our method does capture event selection bias, but whether it captures framing bias requires further investigation.

pdf bib
Exploiting Microblog Conversation Structures to Detect Rumors
Jiawen Li | Yudianto Sujana | Hung-Yu Kao
Proceedings of the 28th International Conference on Computational Linguistics

As one of the most popular social media platforms, Twitter has become a primary source of information for many people. Unfortunately, both valid information and rumors are propagated on Twitter due to the lack of an automatic information verification system. Twitter users communicate by replying to other users’ messages, forming a conversation structure. Using this structure, users can decide whether the information in the source tweet is a rumor by reading the tweet’s replies, which voice other users’ stances on the tweet. The majority of rumor detection researchers process such tweets based on time, ignoring the conversation structure. To reap the benefits of the Twitter conversation structure, we developed a model to detect rumors by modeling conversation structure as a graph. Thus, our model’s improved representation of the conversation structure enhances its rumor detection accuracy. The experimental results on two rumor datasets show that our model outperforms several baseline models, including a state-of-the-art model

2019

pdf bib
Probing Neural Network Comprehension of Natural Language Arguments
Timothy Niven | Hung-Yu Kao
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

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. However, we show that this result is entirely accounted for by exploitation of spurious statistical cues in the dataset. We analyze the nature of these cues and demonstrate that a range of models all exploit them. This analysis informs the construction of an adversarial dataset on which all models achieve random accuracy. Our adversarial dataset provides a more robust assessment of argument comprehension and should be adopted as the standard in future work.

pdf bib
Fill the GAP: Exploiting BERT for Pronoun Resolution
Kai-Chou Yang | Timothy Niven | Tzu Hsuan Chou | Hung-Yu Kao
Proceedings of the First Workshop on Gender Bias in Natural Language Processing

In this paper, we describe our entry in the gendered pronoun resolution competition which achieved fourth place without data augmentation. Our method is an ensemble system of BERTs which resolves co-reference in an interaction space. We report four insights from our work: BERT’s representations involve significant redundancy; modeling interaction effects similar to natural language inference models is useful for this task; there is an optimal BERT layer to extract representations for pronoun resolution; and the difference between the attention weights from the pronoun to the candidate entities was highly correlated with the correct label, with interesting implications for future work.

pdf bib
Detecting Argumentative Discourse Acts with Linguistic Alignment
Timothy Niven | Hung-Yu Kao
Proceedings of the 6th Workshop on Argument Mining

We report the results of preliminary investigations into the relationship between linguistic alignment and dialogical argumentation at the level of discourse acts. We annotated a proof of concept dataset with illocutions and transitions at the comment level based on Inference Anchoring Theory. We estimated linguistic alignment across discourse acts and found significant variation. Alignment features calculated at the dyad level are found to be useful for detecting a range of argumentative discourse acts.

2018

pdf bib
NLITrans at SemEval-2018 Task 12: Transfer of Semantic Knowledge for Argument Comprehension
Timothy Niven | Hung-Yu Kao
Proceedings of The 12th International Workshop on Semantic Evaluation

The Argument Reasoning Comprehension Task is a difficult challenge requiring significant language understanding and complex reasoning over world knowledge. We focus on transfer of a sentence encoder to bootstrap more complicated architectures given the small size of the dataset. Our best model uses a pre-trained BiLSTM to encode input sentences, learns task-specific features for the argument and warrants, then performs independent argument-warrant matching. This model achieves mean test set accuracy of 61.31%. Encoder transfer yields a significant gain to our best model over random initialization. Sharing parameters for independent warrant evaluation provides regularization and effectively doubles the size of the dataset. We demonstrate that regularization comes from ignoring statistical correlations between warrant positions. We also report an experiment with our best model that only matches warrants to reasons, ignoring claims. Performance is still competitive, suggesting that our model is not necessarily learning the intended task.

2017

pdf bib
IKM at SemEval-2017 Task 8: Convolutional Neural Networks for stance detection and rumor verification
Yi-Chin Chen | Zhao-Yang Liu | Hung-Yu Kao
Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017)

This paper describes our approach for SemEval-2017 Task 8. We aim at detecting the stance of tweets and determining the veracity of the given rumor. We utilize a convolutional neural network for short text categorization using multiple filter sizes. Our approach beats the baseline classifiers on different event data with good F1 scores. The best of our submitted runs achieves rank 1st among all scores on subtask B.

2016

pdf bib
Proceedings of the 28th Conference on Computational Linguistics and Speech Processing (ROCLING 2016)
Chung-Hsien Wu | Yuen-Hsien Tseng | Hung-Yu Kao
Proceedings of the 28th Conference on Computational Linguistics and Speech Processing (ROCLING 2016)

2015

pdf bib
Word Co-occurrence Augmented Topic Model in Short Text
Guan-Bin Chen | Hung-Yu Kao
Proceedings of the 27th Conference on Computational Linguistics and Speech Processing (ROCLING 2015)

pdf bib
International Journal of Computational Linguistics & Chinese Language Processing, Volume 20, Number 2, December 2015 - Special Issue on Selected Papers from ROCLING XXVII
Hung-Yu Kao | Yih-Ru Wang | Jen-Tzong Chien
International Journal of Computational Linguistics & Chinese Language Processing, Volume 20, Number 2, December 2015 - Special Issue on Selected Papers from ROCLING XXVII

pdf bib
Word Co-occurrence Augmented Topic Model in Short Text
Guan-Bin Chen | Hung-Yu Kao
International Journal of Computational Linguistics & Chinese Language Processing, Volume 20, Number 2, December 2015 - Special Issue on Selected Papers from ROCLING XXVII

2014

pdf bib
International Journal of Computational Linguistics & Chinese Language Processing, Volume 19, Number 4, December 2014 - Special Issue on Selected Papers from ROCLING XXVI
Jen-Tzung Chien | Hung-Yu Kao | Chia-Hui Chang
International Journal of Computational Linguistics & Chinese Language Processing, Volume 19, Number 4, December 2014 - Special Issue on Selected Papers from ROCLING XXVI

2013

pdf bib
Constructing Social Intentional Corpora to Predict Click-Through Rate for Search Advertising
Yi-Ting Chen | Hung-Yu Kao
Proceedings of the 25th Conference on Computational Linguistics and Speech Processing (ROCLING 2013)