Joseph Marvin Imperial

Kumusta! I'm Joseph. I'm a UKRI CDT Doctoral Researcher at the University of Bath's Integrated Ph.D. Program in Accountable, Responsible, and Transparent AI (also called ART-AI)

I do state-of-the-art research in Natural Language Processing (NLP) and Machine Learning (ML). I'm particularly interested in the following research areas:

I'm originally from the Philippines but am currently based in the UK for the rest of my Ph.D. studies. I'm also affiliated as a faculty member with the Department of Computer Science and as an NLP researcher of the Human Language Technology (HLT) Lab at National University, Philippines.

You may visit my  Google Scholar page for the complete list of my previous research engagements.

If you need to contact me for general queries, collaborations, or questions about my research, click this to redirect you to the contact details page.

Updates

May 8, 2024 - I have been awarded the Doctoral Recognition Award 2024 for my research in NLP by the University of Bath Doctoral College.

May 2, 2024 - Our new position paper Near to Mid-term Risks and Opportunities of Open Source Generative AI has been accepted as ORAL for ICML 2024. Work led by University of Oxford and supported by Meta. Paper can be found here.

April 17, 2024 - Our new AI Safety Benchmark, containing 40k+ prompts for evaluating GenAI models for harms and hazard categories, is now published at IEEE Spectrum and on Arxiv. Work led by the MLCommons AI Safety Group.

March 13, 2024 - Our paper Universal NER: A Gold-Standard Multilingual Named Entity Recognition Benchmark has been accepted to NAACL 2024 (Main). The project website and paper can be found here.

March 1, 2024 - A new paper on aligning language models with expert standards entitled Standardize: Aligning Language Models with Expert-Defined Standards for Content Generation. The project website and paper can be found here.

February 29, 2024 - I'm happy to be elected as a Regular Member of the DOST National Research Council of the Philippines (NRCP) under the Mathematical Sciences Division. The NRCP promotes fundamental and applied research for the continuing total improvement of the country's capabilities in science and technology.

February 1, 2024 - I'm co-organizing a Shared Task on Multilingual Lexical Simplification Pipeline (MLSP) to be hosted at the BEA Workshop in NAACL 2024. See official website to join here.

December 5, 2023 - I'm happy to present three first-authored papers at EMNLP 2023 in Singapore covering low-resource readability assessment and evaluation of LLMs for text generation. See Papers tab for more details.

November 30, 2023 - I'm excited to attend as an invited speaker to share my research on evaluating LLMs for education at Meta AI's Open Innovation AI Research Community, a two-day workshop on developing governance principles for foundational models.

October 1, 2023 - I have upcoming NLP talks at the University of Manchester, the University of Toronto, Ontario Tech University, and NRC Canada this November. 

July 11, 2023 - I'm thrilled to be recognized as an Outstanding Reviewer (Top 1% of 4490 reviewers) at ACL 2023. Thank you to the ACs, SACs, and PCs for this prestigious recognition! See the list here.

May 2, 2023 - Our long paper entitled Automatic Readability Assessment for Closely Related Languages has been accepted to ACL 2023. Work with Ekaterina Kochmar from MBZUAI. Code and paper can be found here.

March 28, 2023 - I received the National University Philippines' pioneer Researcher of the Year Award for contributing to Natural Language Processing research and the university's research goals.