Andrew Parry

profile.jpg

Room 502, Level 5

Sir Alwyn Williams Building

Glasgow, G12 8QQ

I am a 3rd year PhD Candidate at the University of Glasgow working within the IR group. I am supervised by Dr Debasis Ganguly and Dr Sean MacAvaney. My research interests are primarily in Information Retrieval. Before my PhD I completed my honours degree in Computer Science at Glasgow.

My thesis is focused on inducing control over neural models without post-hoc constraint and how we can incorporate broader features in semantic interactions. A relatively up to date CV can be found here. Reach out on Twitter or by email if you want to chat about research or code. I’m generally interested in collaborations centred around robustness of neural systems under adversarial settings and semi-supervised signals in NLP.

news

Sep 23, 2024 Our resource paper is accepted into SIGIR-AP 2024!
Sep 20, 2024 Our full paper is accepted into EMNLP 2024 Findings!
Jun 08, 2024 Our full paper is accepted into ReNeuIR@SIGIR 2024!
May 16, 2024 Our full paper is accepted into ACL 2024 findings!
Apr 15, 2024 Our perspective paper and my doctoral consortium paper have been accepted to SIGIR 2024!

selected publications

  1. ACL’24
    Exploiting Positional Bias for Query-Agnostic Generative Content in Search
    Andrew ParrySean MacAvaney, and Debasis Ganguly
    In Findings of the Association for Computational Linguistics ACL 2024 , Aug 2024
  2. SIGIR’24
    "In-Context Learning" or: How I learned to stop worrying and love "Applied Information Retrieval"
    Andrew ParryDebasis Ganguly, and Manish Chandra
    SIGIR 2024, May 2024
    arXiv:2405.01116 [cs]
  3. SIGIR’24
    "Axiomatic Guidance for Efficient and Controlled Neural Search"
    Andrew Parry
    SIGIR 2024, May 2024
  4. ECIR’24
    Analyzing Adversarial Attacks on Sequence-to-Sequence Relevance Models
    Andrew Parry, Maik Fröbe, Sean MacAvaney, Martin Potthast, and Matthias Hagen
    ECIR, May 2024
    Book Title: Advances in Information Retrieval ISBN: 9783031560590 9783031560606 Place: Cham Publisher: Springer Nature Switzerland
  5. ReNeuIR@SIGIR’24
    Top-Down Partitioning for Efficient List-Wise Ranking
    Andrew ParrySean MacAvaney, and Debasis Ganguly
    ReNeuIR@SIGIR 2024, May 2024