Papers by Ting-Hao Huang
Assessing the Helpfulness of Learning Materials with Inference-Based Learner-Like Agent (2020.emnlp-main)
Copied to clipboard
| Challenge: | Prior work uses hand-crafted scores to recommend sentences but has difficulty adopting such scores to all the near-synonyms as near-near-sonyms differ in various ways. |
| Approach: | They propose an inference-based learner-like agent to mimic learner behavior and identify good learning materials by examining the agent's performance. |
| Outcome: | The proposed agent achieves the best performance in fill-in-the-blank and good example sentence selection tasks. |
Learning to Rank Visual Stories From Human Ranking Data (2022.acl-long)
Copied to clipboard
| Challenge: | Existing studies on visual storytelling (VIST) use automated evaluation metrics for text generation. |
| Approach: | They develop a Vrank metric that repurposes human evaluation results for automatic evaluation. |
| Outcome: | The proposed model is more accurate than existing metrics and is generalizable to textual stories. |
GPT-4 as an Effective Zero-Shot Evaluator for Scientific Figure Captions (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing algorithms that generate captions for scientific figures are costly and dependent on author-written captions. |
| Approach: | They constructed a human evaluation dataset that contains human judgments for 3,600 scientific figure captions for 600 arXiv figures. |
| Outcome: | The proposed model outperforms all other models and outperformed undergraduates in achieving a Kendall correlation score of 0.401 with Ph.D. students’ rankings. |
EmotionLines: An Emotion Corpus of Multi-Party Conversations (L18-1)
Copied to clipboard
| Challenge: | Emotion is a critical characteristic to distinguish people from machines. |
| Approach: | They propose a dataset with emotions labeling on all utterances in each dialogue . they use Friends TV scripts and Facebook messenger dialogues to collect the data . |
| Outcome: | The proposed dataset is the first with emotions labeling on all utterances in each dialogue based on their textual content. |
Multi-VQG: Generating Engaging Questions for Multiple Images (2022.emnlp-main)
Copied to clipboard
| Challenge: | Traditional visual question generation (VQG) focuses on single images, resulting in a limited ability to comprehend time-series information of the underlying event. |
| Approach: | They propose to generate engaging questions from multiple images using a visual question generation dataset and establish a series of baselines. |
| Outcome: | The proposed model builds stories behind the image sequence to allow for creativity and experience sharing and hence draw attention to downstream applications. |
Semantic Frame Forecast (2021.naacl-main)
Copied to clipboard
| Challenge: | Prior work focused on predicting the immediate future of a story, such as one to a few sentences ahead. |
| Approach: | They propose a task that predicts the semantic frames that will occur in the next 10, 100, or even 1,000 sentences in a running story. |
| Outcome: | The proposed model outperforms random, prior, and replay baselines when the block size is over 150 sentences. |
SciCap: Generating Captions for Scientific Figures (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Low-quality captions are common in scientific articles and can decrease understanding . this paper aims to develop an end-to-end neural framework to generate informative, high-quality figure captions for scientific figures and charts. |
| Approach: | They propose an end-to-end neural framework to automatically generate captions for scientific figures from a large-scale dataset . they used figure-type classification, sub-figure identification, text normalization, and caption text selection to build models that caption graph plots, the dominant figure type. |
| Outcome: | The proposed model can generate high-quality captions for scientific figures and charts from a large figure-caption dataset from arXiv. |
Plot and Rework: Modeling Storylines for Visual Storytelling (2021.findings-acl)
Copied to clipboard
| Challenge: | Automated visual storytelling models do not make extensive use of external knowledge and iterative generation when attempting to create stories. |
| Approach: | They propose a framework that uses an image sequence as a story graph to create a coherent story. |
| Outcome: | The proposed framework produces stories superior in diversity, coherence, and humanness . it uses plotting and reworking to improve the model's performance, the authors say . |
Stretch-VST: Getting Flexible With Visual Stories (2021.acl-demo)
Copied to clipboard
| Challenge: | Existing visual storytelling models produce stories with fixed lengths of five sentences and the fix-length stories carry limited details and provide ambiguous textual information to the readers. |
| Approach: | They propose to “stretch” visual storytelling frameworks by adding appropriate knowledge to the model to generate long stories. |
| Outcome: | The proposed framework provides better focus and detail when long stories are generated without deteriorating the quality. |
ABCD: A Graph Framework to Convert Complex Sentences to a Covering Set of Simple Sentences (2021.acl-long)
Copied to clipboard
| Challenge: | Existing work relies on rule-based methods dependent on parsing to identify atomic sentences. |
| Approach: | They propose a task to decompose complex sentences into simple ones . they propose atomic clauses as atomic sentences, and a graph edit task to predict edits . |
| Outcome: | The proposed model performs better than baselines on MinWiki and DeSSE. |
Are Shortest Rationales the Best Explanations for Human Understanding? (2022.acl-short)
Copied to clipboard
| Challenge: | Existing models favor extracting the shortest possible rationales to explain model predictions . however, this assumption has yet to be validated . |
| Approach: | They propose a model that extracts rationales at any target length from text inputs . they show that rationale lengths too short do not help humans predict labels better . |
| Outcome: | The proposed model achieves compatible end-task performance and human-annotated rationale agreement compared to baseline models . |
Do Large Multimodal Models Solve Caption Generation for Scientific Figures? Lessons Learned from SciCap Challenge 2023 (2026.tacl-1)
Copied to clipboard
Ting-Yao Hsu, Yi-Li Hsu, Shaurya Rohatgi, Chieh-Yang Huang, Ho Yin Sam Ng, Ryan Rossi, Sungchul Kim, Tong Yu, Lun-Wei Ku, Clyde Lee Giles, Ting-Hao Huang
| Challenge: | SciCap dataset launched in 2021 aims to generate high-quality captions for scientific figures. |
| Approach: | They propose to use the SciCap dataset to develop models for captioning diverse figure types across various academic fields. |
| Outcome: | The proposed models showed impressive performance on the SciCap dataset and in various vision-and-language tasks. |
FinQA: A Dataset of Numerical Reasoning over Financial Data (2021.emnlp-main)
Copied to clipboard
Zhiyu Chen, Wenhu Chen, Charese Smiley, Sameena Shah, Iana Borova, Dylan Langdon, Reema Moussa, Matt Beane, Ting-Hao Huang, Bryan Routledge, William Yang Wang
| Challenge: | Popular, large, pre-trained models fall far short of expert humans in acquiring finance knowledge and in complex multi-step numerical reasoning on that knowledge. |
| Approach: | They propose a large-scale dataset with Question-Answering pairs over financial reports written by financial experts to facilitate analytical progress. |
| Outcome: | The proposed dataset is the first of its kind and is available on github. |
Location-Aware Visual Question Generation with Lightweight Models (2023.emnlp-main)
Copied to clipboard
Nicholas Suwono, Justin Chen, Tun Hung, Ting-Hao Huang, I-Bin Liao, Yung-Hui Li, Lun-Wei Ku, Shao-Hua Sun
| Challenge: | a novel task aims to generate engaging questions from location-aware information . a lightweight model can be used to generate such questions . |
| Approach: | They propose a task to generate engaging questions from location-aware data . they represent location-based information with surrounding images and a GPS coordinate . |
| Outcome: | The proposed method outperforms baselines regarding human evaluation and evaluation metrics. |
Visual Story Post-Editing (P19-1)
Copied to clipboard
| Challenge: | a dataset for human edits of machine-generated visual stories is released . it includes 14,905 human-edited versions of 2,981 machine- generated visual stories . |
| Approach: | They introduce the first dataset for human edits of machine-generated visual stories . they explore how edits may be used for the visual story post-editing task . |
| Outcome: | The proposed dataset includes 14,905 human-edited versions of 2,981 machine-generated visual stories. |
Nationality Bias in Text Generation (2023.eacl-main)
Copied to clipboard
| Challenge: | Existing studies have shown that nationality biases in language models can be a factor in improving the performance of social NLP models. |
| Approach: | They propose to use a text generation model, GPT-2, to analyze how the number of internet users and the country’s economic status affects the sentiment of stories. |
| Outcome: | The proposed model accentuates biases about country-based demonyms and reduces them with the use of adversarial triggering. |
CoCoLoFa: A Dataset of News Comments with Common Logical Fallacies Written by LLM-Assisted Crowds (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing algorithms for detecting logical fallacies in texts are expensive and require large-scale labeled datasets. |
| Approach: | They introduce CoCoLoFa, the largest known logical fallacy dataset, with 7,706 comments for 648 news articles labeled for fallacy presence and type. |
| Outcome: | The proposed dataset outperforms state-of-the-art LLMs in fallacy detection and classification. |