Josiah Poon
16 papers · 2020–2025 · 9 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+10 more ↓ Show less ↑
π Interdisciplinary Bridge π Renaissance Researcher (6) π Academic Marathon (5) π Conference Polyglot (9) πΊοΈ Taxonomy Completionist (31)
πΊοΈ
Taxonomy Completionist
(31)
π§
Keyword Pioneer
π£
Hot Topic Early Bird
π€
Dynamic Duo
(10)
π§¬
Topic Evolution
π
Century Club
(16)
β
The Questioner
ποΈ
Keyword Collector
(80)
π₯
Unstoppable
(6)
β‘
Prolific Year
(5)
Conferences
COLING (4)
EMNLP (3)
ACL (2)
INTERSPEECH (2)
EACL (1)
IJCAI (1)
IJCNLP (1)
NAACL (1)
WACV (1)
Top co-authors
Keywords
multimodal learning
(5)
graph neural network
(3)
graph representation
(2)
natural language understanding
(2)
information extraction
(2)
visual storytelling
(2)
joint learning
(2)
slot filling
(2)
graph convolutional network
(2)
embedding learning
(1)
named entity recognition
(1)
object detection
(1)
abusive language detection
(1)
multi-task learning
(1)
relation extraction
(1)
knowledge distillation
(1)
natural language processing
(1)
empirical study
(1)
document parsing
(1)
text representation
(1)
Papers
VRD-IU: Lessons from Visually Rich Document Intelligence and Understanding
IJCAI 2025
SCO-VIST: Social Interaction Commonsense Knowledge-based Visual Storytelling
EACL 2024
Do Text-to-Vis Benchmarks Test Real Use of Visualisations?
EMNLP 2024
3MVRD: Multimodal Multi-task Multi-teacher Visually-Rich Form Document Understanding
ACL 2024
Re-Temp: Relation-Aware Temporal Representation Learning for Temporal Knowledge Graph Completion
EMNLP 2023
Tri-level Joint Natural Language Understanding for Multi-turn Conversational Datasets
INTERSPEECH 2023
GraDual: Graph-Based Dual-Modal Representation for Image-Text Matching
WACV 2022
Doc-GCN: Heterogeneous Graph Convolutional Networks for Document Layout Analysis
COLING 2022
Understanding Attention for Vision-and-Language Tasks
COLING 2022
DDI-MuG: Multi-aspect Graphs for Drug-Drug Interaction Extraction
EMNLP 2022
RoViST: Learning Robust Metrics for Visual Storytelling
NAACL 2022
CONDA: a CONtextual Dual-Annotated dataset for in-game toxicity understanding and detection
IJCNLP 2021
Bi-Directional Joint Neural Networks for Intent Classification and Slot Filling
INTERSPEECH 2021
CONDA: a CONtextual Dual-Annotated dataset for in-game toxicity understanding and detection
ACL 2021
VICTR: Visual Information Captured Text Representation for Text-to-Vision Multimodal Tasks
COLING 2020
Detect All Abuse! Toward Universal Abusive Language Detection Models
COLING 2020