M.J Jang

Myeongjun Jang
Wolfson Building, Parks Road, Oxford OX1 3QD
Interests
Natural Language Understanding, Consistent and Trustworthy Language Model, Logical Reasoning.
Biography
M.J is a DPhil student in Computer Science at the University of Oxford. His current research focuses on investigating inconsistent behaviours of neural language models and developing remedies to alleviate the issues. M.J received a B.Sc degree in Industrial Management Engineering from Korea University in 2017 and earned an M.Eng degree in 2019 from the same affiliation. M.J has previously worked for SK Telecom in Seoul, South Korea, as a natural language processing (NLP) scientist & engineer from 2019 to 2020.
Selected Publications
-
Beyond Distributional Hypothesis: Let Language Models Learn Meaning−Text Correspondence
Myeongjun Jang‚ Frank Martin Mtumbuka and Thomas Lukasiewicz
In Findings of NAACL 2022‚ Seattle‚ Washington‚ USA‚ July 2022. Association for Computational Linguistics. 2022.
Details about Beyond Distributional Hypothesis: Let Language Models Learn Meaning−Text Correspondence | BibTeX data for Beyond Distributional Hypothesis: Let Language Models Learn Meaning−Text Correspondence | Link to Beyond Distributional Hypothesis: Let Language Models Learn Meaning−Text Correspondence
-
Learning−Free Unsupervised Extractive Summarization Model
Myeongjun Jang and Pilsung Kang
In IEEE Access. Vol. 9. Pages 14358−14368. 2021.
Details about Learning−Free Unsupervised Extractive Summarization Model | BibTeX data for Learning−Free Unsupervised Extractive Summarization Model | DOI (10.1109/ACCESS.2021.3051237)