56 citations · 146 across the 29 of their papers we have counts for
21 papers · 1 filter
From Papers to Panoramas: Building Hierarchies of Scientific Literature at Scale
Muhan Gao, Jash Shah, Weiqi Wang +2
Scientific knowledge is growing rapidly, making it difficult to track progress and high-level conceptual links across broad disciplines. While tools like citation networks and sear…
Eliminating Position Bias of Language Models: A Mechanistic Approach
Ziqi Wang, Hanlin Zhang, Xiner Li +6
Position bias has proven to be a prevalent issue of modern language models (LMs), where the models prioritize content based on its position within the given context. This bias ofte…
Event Detection from Social Media for Epidemic Prediction
Tanmay Parekh, Anh Mac, Jiarui Yu +8
Social media is an easy-to-access platform providing timely updates about societal trends and events. Discussions regarding epidemic-related events such as infections, symptoms, an…
Visually Descriptive Language Model for Vector Graphics Reasoning
Zhenhailong Wang, Joy Hsu, Xingyao Wang +4
Despite significant advancements, large multimodal models (LMMs) still struggle to bridge the gap between low-level visual perception -- focusing on shapes, sizes, and layouts -- a…
TextEE: Benchmark, Reevaluation, Reflections, and Future Challenges in Event Extraction
Kuan-Hao Huang, I-Hung Hsu, Tanmay Parekh +6
Event extraction has gained considerable interest due to its wide-ranging applications. However, recent studies draw attention to evaluation issues, suggesting that reported scores…
Self-Augmentation Improves Zero-Shot Cross-Lingual Transfer
Fei Wang, Kuan-Hao Huang, Kai-Wei Chang +1
Zero-shot cross-lingual transfer is a central task in multilingual NLP, allowing models trained in languages with more sufficient training resources to generalize to other low-reso…
Contextual Label Projection for Cross-Lingual Structured Prediction
Tanmay Parekh, I-Hung Hsu, Kuan-Hao Huang +2
Label projection, which involves obtaining translated labels and texts jointly, is essential for leveraging machine translation to facilitate cross-lingual transfer in structured p…
AMPERE: AMR-Aware Prefix for Generation-Based Event Argument Extraction Model
I-Hung Hsu, Zhiyu Xie, Kuan-Hao Huang +2
Event argument extraction (EAE) identifies event arguments and their specific roles for a given event. Recent advancement in generation-based EAE models has shown great performance…
PIP: Parse-Instructed Prefix for Syntactically Controlled Paraphrase Generation
Yixin Wan, Kuan-Hao Huang, Kai-Wei Chang
Syntactically controlled paraphrase generation requires language models to generate paraphrases for sentences according to specific syntactic structures. Existing fine-tuning metho…
ParaAMR: A Large-Scale Syntactically Diverse Paraphrase Dataset by AMR Back-Translation
Kuan-Hao Huang, Varun Iyer, I-Hung Hsu +3
Paraphrase generation is a long-standing task in natural language processing (NLP). Supervised paraphrase generation models, which rely on human-annotated paraphrase pairs, are cos…
Understanding and Mitigating Spurious Correlations in Text Classification with Neighborhood Analysis
Oscar Chew, Hsuan-Tien Lin, Kai-Wei Chang +1
Recent research has revealed that machine learning models have a tendency to leverage spurious correlations that exist in the training set but may not hold true in general circumst…
Learning Easily Updated General Purpose Text Representations with Adaptable Task-Specific Prefixes
Kuan-Hao Huang, Liang Tan, Rui Hou +3
Many real-world applications require making multiple predictions from the same text. Fine-tuning a large pre-trained language model for each downstream task causes computational bu…
Unsupervised Syntactically Controlled Paraphrase Generation with Abstract Meaning Representations
Kuan-Hao Huang, Varun Iyer, Anoop Kumar +3
Syntactically controlled paraphrase generation has become an emerging research direction in recent years. Most existing approaches require annotated paraphrase pairs for training a…
TAGPRIME: A Unified Framework for Relational Structure Extraction
I-Hung Hsu, Kuan-Hao Huang, Shuning Zhang +4
Many tasks in natural language processing require the extraction of relationship information for a given condition, such as event argument extraction, relation extraction, and task…
GENEVA: Benchmarking Generalizability for Event Argument Extraction with Hundreds of Event Types and Argument Roles
Tanmay Parekh, I-Hung Hsu, Kuan-Hao Huang +2
Recent works in Event Argument Extraction (EAE) have focused on improving model generalizability to cater to new events and domains. However, standard benchmarking datasets like AC…
Multilingual Generative Language Models for Zero-Shot Cross-Lingual Event Argument Extraction
Kuan-Hao Huang, I-Hung Hsu, Premkumar Natarajan +2
We present a study on leveraging multilingual pre-trained generative language models for zero-shot cross-lingual event argument extraction (EAE). By formulating EAE as a language g…
DEGREE: A Data-Efficient Generation-Based Event Extraction Model
I-Hung Hsu, Kuan-Hao Huang, Elizabeth Boschee +4
Event extraction requires high-quality expert human annotations, which are usually expensive. Therefore, learning a data-efficient event extraction model that can be trained with o…
Disentangling Semantics and Syntax in Sentence Embeddings with Pre-trained Language Models
James Y. Huang, Kuan-Hao Huang, Kai-Wei Chang
Pre-trained language models have achieved huge success on a wide range of NLP tasks. However, contextual representations from pre-trained models contain entangled semantic and synt…
Improving Zero-Shot Cross-Lingual Transfer Learning via Robust Training
Kuan-Hao Huang, Wasi Uddin Ahmad, Nanyun Peng +1
Pre-trained multilingual language encoders, such as multilingual BERT and XLM-R, show great potential for zero-shot cross-lingual transfer. However, these multilingual encoders do…
Generating Syntactically Controlled Paraphrases without Using Annotated Parallel Pairs
Kuan-Hao Huang, Kai-Wei Chang
Paraphrase generation plays an essential role in natural language process (NLP), and it has many downstream applications. However, training supervised paraphrase models requires ma…
Examining Gender Bias in Languages with Grammatical Gender
Pei Zhou, Weijia Shi, Jieyu Zhao +4
Recent studies have shown that word embeddings exhibit gender bias inherited from the training corpora. However, most studies to date have focused on quantifying and mitigating suc…