LaKo: Knowledge-driven Visual Question Answering via Late Knowledge-to-Text Injection

1 code implementation • 26 Jul 2022 • Zhuo Chen, Yufeng Huang, Jiaoyan Chen, Yuxia Geng, Yin Fang, Jeff Pan, Ningyu Zhang, Wen Zhang

Visual question answering (VQA) often requires an understanding of visual concepts and language semantics, which relies on external knowledge.

Decoder Knowledge Graphs +3

Learning from Ontology Streams with Semantic Concept Drift

no code implementations • 24 Apr 2017 • Freddy Lecue, Jiaoyan Chen, Jeff Pan, Huajun Chen

Data stream learning has been largely studied for extracting knowledge structures from continuous and rapid data records.

Passing a USA National Bar Exam: a First Corpus for Experimentation

no code implementations • LREC 2016 • Biralatei Fawei, Adam Wyner, Jeff Pan

The paper provides a corpus and experimental results with material derived from a real bar exam, treating the problem as a form of textual entailment from the question to an answer.

Natural Language Inference