Code generation for few-shot event structure prediction
Wang, Xingyao
This item is only available for download by members of the University of Illinois community. Students, faculty, and staff at the U of I may log in with your NetID and password to view the item. If you are trying to access an Illinois-restricted dissertation or thesis, you can request a copy through your library's Inter-Library Loan office or purchase a copy directly from ProQuest.
Permalink
https://hdl.handle.net/2142/125694
Description
Title
Code generation for few-shot event structure prediction
Author(s)
Wang, Xingyao
Issue Date
2024-07-08
Director of Research (if dissertation) or Advisor (if thesis)
Ji, Heng
Department of Study
Siebel Computing &DataScience
Discipline
Computer Science
Degree Granting Institution
University of Illinois at Urbana-Champaign
Degree Name
M.S.
Degree Level
Thesis
Keyword(s)
event argument extraction
code generation
large language model
Abstract
Large Language Model (LLM) trained on a mixture of text and code has demonstrated impressive capability in translating natural language (NL) into structured code. We observe that semantic structures can be conveniently translated into code and propose Code4Struct to leverage such text-to-structure translation capability to tackle structured prediction tasks. As a case study, we formulate Event Argument Extraction (EAE) as converting text into event-argument structures that can be represented as a class object using code. This alignment between structures and code enables us to take advantage of Programming Language (PL) features such as inheritance and type annotation to introduce external knowledge or add constraints. We show that, with sufficient in-context examples, formulating EAE as a code generation problem is advantageous over using variants of text-based prompts. Despite only using 20 training event instances for each event type, Code4Struct is comparable to supervised models trained on 4,202 instances and outperforms current state-of-the-art (SOTA) trained on 20-shot data by 29.5% absolute F1. By leveraging the inheritance feature of PL, Code4Struct can use 10-shot training data from a sibling event type to predict arguments for zero-resource event types and outperforms the zero-shot baseline by 12% absolute F1. All code and resources are publicly available at https://github.com/xingyaoww/code4struct.
Use this login method if you
don't
have an
@illinois.edu
email address.
(Oops, I do have one)
IDEALS migrated to a new platform on June 23, 2022. If you created
your account prior to this date, you will have to reset your password
using the forgot-password link below.
