Papers by Hung-Yu Kao
Unsupervised Extractive Summarization-Based Representations for Accurate and Explainable Collaborative Filtering (2021.acl-long)
Copied to clipboard
| Challenge: | Existing extractive summarization-based collaborative filtering models learn accurate representations of users and items based on user-given numeric ratings, but employing them is an oversimplification of user preferences and item characteristics. |
| Approach: | They propose to use BERT, K-Means embedding clustering, and multilayer perceptron to learn sentence embeddations, representation-explanations, and user-item interactions to create extractive summaries. |
| Outcome: | The proposed model improves rating prediction accuracy and user/item explainability. |
BERT-Based Neural Collaborative Filtering and Fixed-Length Contiguous Tokens Explanation (2020.aacl-main)
Copied to clipboard
| Challenge: | Existing models that learn accurate representations of users and items are based on ratings, which oversimplify user preferences and item characteristics. |
| Approach: | They propose a novel, accurate, and explainable recommender model that integrates three key elements: BERT, multilayer perceptron, and maximum subarray problem to derive contextualized review features, model user-item interactions, and generate explanations. |
| Outcome: | The proposed model outperforms state-of-the-art models by an improvement gain of nearly 7% based on the human judges’ assessment . |
Improving Multi-Criteria Chinese Word Segmentation through Learning Sentence Representation (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Recent Chinese word segmentation models tend to learn the segmentation knowledge through in-vocabulary words rather than understanding the meaning of the entire context. |
| Approach: | They propose a context-aware approach that incorporates unsupervised sentence representation learning over different dropout masks into the multi-criteria training framework. |
| Outcome: | The proposed approach achieves state-of-the-art (SoTA) performance on six of the nine CWS benchmark datasets and out-of vocabulary (OOV) recalls for eight of nine. |
Improved Unsupervised Chinese Word Segmentation Using Pre-trained Knowledge and Pseudo-labeling Transfer (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to unsupervised Chinese word segmentation require multiple inferences to perform word segmenting. |
| Approach: | They propose a method that integrates the segmentation signal from an unsupervised language model to a pre-trained BERT classifier under a pseudo-labeling framework. |
| Outcome: | The proposed method achieves state-of-the-art performance on the eight UCWS tasks while significantly reducing training time compared to previous approaches. |
Unsupervised Single Document Abstractive Summarization using Semantic Units (2022.aacl-main)
Copied to clipboard
| Challenge: | a lack of sufficient training pairs is a common issue in real-world applications. |
| Approach: | They propose a framework that lets a model learn the frequency of each semantic unit in the source text. |
| Outcome: | The proposed model outperforms other unsupervised methods under CNN/Daily Mail task. |
Rumor Detection on Twitter Using Multiloss Hierarchical BiLSTM with an Attenuation Factor (2020.aacl-main)
Copied to clipboard
| Challenge: | Existing models to classify rumors have low precision and are time consuming. |
| Approach: | They propose a multiloss hierarchical biLSTM model with an attenuation factor that can extract deep information from limited quantities of text. |
| Outcome: | The proposed model can extract deep information from limited quantities of text. |
R-AT: Regularized Adversarial Training for Natural Language Understanding (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Currently, adversarial training is a popular and powerful regularization method in the natural language domain. |
| Approach: | They propose to regularize adversarial training via dropout by perturbing word embeddings . they find that R-AT can improve many models by reducing adversariality . |
| Outcome: | The proposed method can reduce the inconsistency between training and testing of models with dropout. |
Meet The Truth: Leverage Objective Facts and Subjective Views for Interpretable Rumor Detection (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing rumor detection methods provide detection labels while ignoring their explanation. |
| Approach: | a novel model is proposed to automatically classify rumors using Wikipedia documents . the model combines objective facts and subjective views to verify rumours . |
| Outcome: | a new model outperforms existing models on real-world Twitter datasets . the proposed model combines objective facts and subjective views to verify rumor . |
Breaking Boundaries in Retrieval Systems: Unsupervised Domain Adaptation with Denoise-Finetuning (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing domain adaptation methods for dense retrieval models use unadapted rerank models, leading to imprecise labels. |
| Approach: | They propose to adapt a rerank model to the target domain before using it for label generation. |
| Outcome: | The proposed model achieves better results across three retrieval datasets. |
Advancing Multi-Criteria Chinese Word Segmentation Through Criterion Classification and Denoising (2023.acl-long)
Copied to clipboard
| Challenge: | Recent research on multi-criteria Chinese word segmentation focuses on building complex private structures, adding more handcrafted features, or introducing complex optimization processes. |
| Approach: | They propose a model that fits multiple Chinese word segments using input-hint inputs. |
| Outcome: | The proposed model achieves state-of-the-art (SoTA) performance on multiple datasets simultaneously. |
Exploiting Microblog Conversation Structures to Detect Rumors (2020.coling-main)
Copied to clipboard
| Challenge: | Existing models for rumor detection ignore the conversation structure of tweets . 68% of american adults occasionally read news on social media platforms . however, the credibility of news propagated through social media is questionable due to the lack of editors who can validate it. |
| Approach: | They propose to model Twitter conversation structure by modeling it as a graph to detect rumors by reading tweets that voice other users’ stances on the tweet. |
| Outcome: | The proposed model outperforms baseline models on two rumor datasets and shows that it outperformed several baseline models. |
Probing Neural Network Comprehension of Natural Language Arguments (P19-1)
Copied to clipboard
| Challenge: | Argument Reasoning Comprehension Task (ARCT) focuses on inferences, not just discovering warrants. |
| Approach: | They propose to build an adversarial dataset on which all models achieve random accuracy. |
| Outcome: | The proposed dataset provides a more robust assessment of argument comprehension and should be adopted as the standard in future work. |
MAPLE: Enhancing Review Generation with Multi-Aspect Prompt LEarning in Explainable Recommendation (2025.acl-long)
Copied to clipboard
Ching-Wen Yang, Zhi-Quan Feng, Ying-Jia Lin, Che Wei Chen, Kun-da Wu, Hao Xu, Yao Jui-Feng, Hung-Yu Kao
| Challenge: | Existing models that generate generic aspects do not provide personalized informative recommendations. |
| Approach: | They propose a model that integrates aspect category as another input dimension to facilitate memorizing fine-grained aspect terms. |
| Outcome: | The proposed model outperforms baseline model on restaurant review datasets in the restaurant domain. |
SCURank: Ranking Multiple Candidate Summaries with Summary Content Units for Enhanced Summarization (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing ranking strategies for large language models suffer from instability and lack of information content. |
| Approach: | They propose a framework that enhances summarization by leveraging Summary Content Units (SCUs) they investigate the effectiveness of SCURank in distilling summaries from multiple LLMs . |
| Outcome: | The proposed framework outperforms traditional metrics and LLM-based ranking methods in summarization tasks. |