Papers by Te-Lin Wu

9 papers
HyperExpan: Taxonomy Expansion with Hyperbolic Representation Learning (2021.findings-emnlp)

Copied to clipboard

Challenge: Existing taxonomies have limited coverage due to expensive manual curation process.
Approach: They propose an algorithm that expands existing taxonomies to preserve their structure in a more expressive hyperbolic embedding space and learns to represent concepts and their relations with a hyperbolical Graph Neural Network.
Outcome: The proposed algorithm outperforms baseline models with representation learning in a Euclidean feature space and achieves state-of-the-art performance on the taxonomy expansion benchmarks.
LegalDiscourse: Interpreting When Laws Apply and To Whom (2024.naacl-long)

Copied to clipboard

Challenge: Recent advances in NLP and information retrieval have already enabled practical applications.
Approach: They propose a 'discourse' taxonomy for span-and-relation parsing of legal texts . they use a dataset of 602 state-level law paragraphs with 3,715 discourse spans and 1,671 relations to investigate the increase in liquor licenses and decrease in applicable laws.
Outcome: The proposed model performs poorly at span identification and relation classification, but lags far below human level.
VDebugger: Harnessing Execution Feedback for Debugging Visual Programs (2024.findings-emnlp)

Copied to clipboard

Challenge: Visual programs are executable code generated by large language models to address visual reasoning problems.
Approach: They propose a critic-refiner framework that localizes and debugs visual programs by tracking execution step by step.
Outcome: The proposed framework detects and corrects program errors leveraging detailed execution feedback, improving interpretability and accuracy.
ACQUIRED: A Dataset for Answering Counterfactual Questions In Real-Life Videos (2023.emnlp-main)

Copied to clipboard

Challenge: despite its importance, there are few datasets that cover multimodal counterfactual reasoning . a dataset focusing on this area is limited because of its limited coverage over synthetic environments .
Approach: They develop a video question answering dataset that provides questions on multimodal reasoning . they ask questions about counterfactual hypotheses over visual events .
Outcome: The proposed dataset shows a significant performance gap between models and humans . it provides questions that span physical, social, and temporal dimensions .
SIMMC-VR: A Task-oriented Multimodal Dialog Dataset with Situated and Immersive VR Streams (2023.acl-long)

Copied to clipboard

Challenge: Existing models lack a large-scale benchmark to capture user–assistant interactions . et al., 2022: 145-160.
Approach: They propose a video-grounded task-oriented dialog dataset that captures real-world AI-assisted user scenarios in VR.
Outcome: The proposed dataset captures real-world AI-assisted user scenarios in VR.
Localizing Active Objects from Egocentric Vision with Symbolic World Knowledge (2023.emnlp-main)

Copied to clipboard

Challenge: Existing work on active object grounding from an egocentric perspective is focusing on localizing and tracking active objects that undergo major state change as a result of human actions/interactions to the environment without being told exactly what/where to ground.
Approach: They propose to use a narrated egocentric video dataset to localize and track active objects that undergo major state change as a result of human actions/interactions to the environment without being told exactly what/where to ground.
Outcome: The proposed framework leads to 54% improvement in standard metrics on the TREK-150-OPE-Det localization + tracking task, and >7% improvement in all standard metrics.
Understanding Multimodal Procedural Knowledge by Sequencing Multimodal Instructional Manuals (2022.acl-long)

Copied to clipboard

Challenge: Current machine learning methods are incapable of efficiently utilizing multimodal information.
Approach: They propose to use text-and-image alignment to improve machine learning's performance on multimodal event sequencing.
Outcome: The proposed models perform significantly worse than humans on multimodal event sequencing than humans.
Learning Action Conditions from Instructional Manuals for Instruction Understanding (2023.acl-long)

Copied to clipboard

Challenge: a weakly supervised task is proposed to extract mentions of preconditions and postconditions of actions from instructional manuals.
Approach: They propose a task dubbed action condition inference which extracts mentions of preconditions and postconditions of actions from instructional manuals.
Outcome: The proposed approach improves on the existing models, but still far behind human performance.
Character-centric Story Visualization via Visual Planning and Token Alignment (2022.emnlp-main)

Copied to clipboard

Challenge: Story visualization is a task that requires machines to understand long text inputs and produce a globally consistent image sequence that illustrates the contents of the story.
Approach: They propose to augment VQ-VAE with a text-to-visual-token (transformer) architecture to enable multiple image generation based on a complete story.
Outcome: The proposed method excels at preserving characters and produces higher quality image sequences compared with baselines.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations