Mingyu Derek Ma

PhD Student

    UCLA Computer Science
derek.ma at ucla.edu        
he/his/him

Hi!

I am a PhD student in Computer Science at UCLA working with Prof. Wei Wang. I am interested in extracting structured knowledge from unstructed text using generative language models. Specifically, my research unbinds structure prediction models from constraints of data resources, label ontology, document structure, and domain.

I earned my bachelor’s degree in Computing from The Hong Kong Polytechnic University with First Class Honours in 2018, advised by Prof. Qin Lu and Prof. Jiannong Cao. I studied as an exchange student at the University of Maryland in 2016. I’ve also spent time at Amazon Alexa AI (working with Dr. Jiun-Yu Kao and Dr. Tagyoung Chung), USC Information Sciences Institute (working with Prof. Nanyun (Violet) Peng and Prof. Muhao Chen), The Chinese University of Hong Kong (working with Prof. Helen Meng), UC Santa Cruz (working with Prof. Marilyn Walker) and MIT (working with Dr. Abel Sanchez and Prof. John R. Williams).

News

Updated preprint!

In STAR, we propose to synthesize training data by structure-to-text generation using Large Language Models and we show that the generated data is even more effective than human-curated data instances to boost the low-resource event extraction performance.

Aug 2023 Presenting at INTERSPEECH 2023 🇮🇪!

TimeLocationActivity
Aug 24 Thu, 10:00-10:20 (IST)Wicklow Hall 1Oral presentation of the conf paper: Parameter-Efficient Low-Resource Dialogue State Tracking by Prompt Tuning. In the collaboration work with Amazon Alexa AI, we introduce a dialogue state tracking model tuning less than 1% of LM parameters and achieves better low-resource performance with prompt tuning techniques.

July 2023 Check out course materials for the 2-week summer program “Data Science for ALL” that were just delivered by our joint team from UCI and UCLA!
July 2023 Presenting at ACL 2023 🇨🇦!

TimeLocationActivity
July 10, 11:00-12:30 (EDT)Metropolitan EastOral presentation of the main conf paper: DICE: Data-Efficient Clinical Event Extraction with Generative Models. We introduce a data-efficient generative model with specialized mention boundary predictions for clinical event extraction. We also propose MACCROBAT-EE, the first benchmark in the domain.
July 10, 19:00-21:00 (EDT)Metropolitan CentreFindings Spotlights of Multi-hop Evidence Retrieval for Cross-document Relation Extraction. We propose a multi-hop evidence retrieval method based on evidence path mining and ranking with dense retrievers, which shows great cross-document relation extraction performance.
July 11, 16:15-17:45 (EDT)Metropolitan CentreOral presentation of the main conf paper: Can NLI Provide Proper Indirect Supervision for Low-resource Biomedical Relation Extraction? We leverage additional cross-domain supervision signals from Natural Language Inference on the Relation Extraction task. We show that it achieves state-of-the-art biomedical RE performance.
July 14, 11:40-12:30 (EDT)Poster presentation at the TrustNLP: Third Workshop on Trustworthy Natural Language Processing

May 2023 New preprints!
In STAR, we propose to synthesize training data by structure-to-text generation using Large Language Models and we show that the generated data is even more effective than human-curated data instances to boost the low-resource event extraction performance.
In the new study about LLM’s backdoor attack, we demonstrate that an attacker can inject backdoors by issuing very few malicious instructions and control model behavior through data poisoning.
May 2023: New INTERSPEECH paper! In the collaboration work with Amazon Alexa AI, we introduce a dialogue state tracking model tuning less than 1% of LM parameters and achieves better low-resource performance with prompt tuning techniques.
Dec 2022: New preprints. We propose to formulate biomedical relation extraction as the NLI task. We design a new evidence retrieval technique for cross-document relation extraction.
Dec 2022: I’ll be at the NeurIPS ENLSP workshop.
Sep 2022: New AKBC paper. In HyperVC, we use hyperbolic models with variable curvature to learn representations of temporal knowledge graphs for future fact prediction.
Aug 2022: New preprint. In DICE, we introduce a data-efficient generative model for clinical event extraction and propose the first benchmark in the domain.
Jun 2022: Started my internship at Amazon Alexa AI working on bias mitigation in Sunnyvale, CA.
May 2022: New preprint. In Summarization as Indirect Supervision for Relation Extraction, we convert the relation extraction task into a summarization formulation.
Aug 2021: New EMNLP Findings paper. In HyperExpan, we use a more expressive hyperbolic space for taxonomy expansion.
Jun 2021: We present our demo system EventPlus at NAACL 2021, the live system and code is released. Check it out!
Jun 2021: My internship at Amazon Alexa AI starts, working on parameter-efficient dialogue state tracking.
Jul 2020 The handbooks for ACL2020 that I helped assemble are ready and they’re available in 24 timezones for the first time, check them out!
May 2020 I’ll move to UCLA this fall.

curriculum vitae

Experience

Education

Awards

  • Outstanding Project Award - Best Capstone Project Award Competition, PolyU Dept. of Computing (1/100) , 2018

    PolyU Computing News

  • HKSAR Government Scholarship Fund Talent Development Scholarship , 2018

  • Silver Award - Hong Kong ICT (Information and Communication Technologies) Awards (website | wiki) Student Innovation Award (Tertiary or Above), Hong Kong Government , 2018

    PolyU News | PolyU Computing News | PolyU Computing News about InnoCarnival Exhibition | PolyU Tweet

  • Champion and Most Innovative Award (HKSAR) - Imagine Cup (website | wiki), Microsoft , 2017
  • Commercial Radio 50th Anniversary Scholarship, Hong Kong Commercial Broadcasting Company Limited & PolyU (1/400) , 2017
  • Winner - Hong Kong Techathon, PolyU and City University of Hong Kong , 2018

    PolyU Computing News | PolyU Tweet

  • CMA (The Chinese Manufacturers’ Association of Hong Kong) & Donors Scholarship (3/100) , 2018

  • Champion - PolyU Smart Computing Competition (website) , 2017

    PolyU Computing News

  • Best Creative Service Project - Youth Volunteer Service Conference (website) , 2017

    News by Office of Service-Learning, PolyU | News by HKSAR Gov Agency for Volunteer Service

  • PolyU Undergraduate Summer Research Abroad Sponsorship , 2017

  • PolyU Chinese Mainland and Overseas Activities Fund , 2016

  • Wong Tit-Shing Student Exchange Scholarship , 2016

  • PolyU Exchange Scholarship , 2016

  • Media Coverage

  • Computer vision app helping the visually impaired: Feature Story by the President of PolyU (Prof. Timothy W. Tong) | at AM730 | Sky Post 晴報 | Ming Pao 明報 | Ta Kung Pao 大公報 | unwire.hk | Sing Tao Daily 星島日報 | IT Pro Magazine | Cool Blind Tech | on.cc 東網 | ifeng.com 鳳凰網 | Wen Wei Po 文匯報 | CCTV 中国中央电视台 | Oriental Daily News 東方日報 | PolyU News | ViuTV (Trailer)
  • Services

  • Reviewer for conferences:
  • Reviewer for journals:
  • Handbook: ACL 2020
  • Volunteer: ACL 2023, SoCal NLP Symposium 2019
  • Teaching

  • Teaching Associate, CS32 Introduction to Computer Science II (Summer 2023) with Prof. Edwin Ambrosio, UCLA
  • Teaching Assistant, Data Science for ALL, an ICS NSF-Funded summer program on data science and machine learning (Summer 2023), UC Irvine & UCLA
  • Teaching Assistant, CS35L Software Construction (Spring 2023) with Prof. Paul Eggert, UCLA
  • Teaching Assistant, CS188 Natural Language Processing (Winter 2022, later became CS162) with Prof. Nanyun (Violet) Peng, UCLA
  • Teaching Assistant, CS31 Introduction to Computer Science I (Fall 2021) with Prof. David Smallberg, UCLA