English

Enhancing Software-Related Information Extraction via Single-Choice Question Answering with Large Language Models

Computation and Language 2024-04-23 v2

Abstract

This paper describes our participation in the Shared Task on Software Mentions Disambiguation (SOMD), with a focus on improving relation extraction in scholarly texts through generative Large Language Models (LLMs) using single-choice question-answering. The methodology prioritises the use of in-context learning capabilities of GLMs to extract software-related entities and their descriptive attributes, such as distributive information. Our approach uses Retrieval-Augmented Generation (RAG) techniques and GLMs for Named Entity Recognition (NER) and Attributive NER to identify relationships between extracted software entities, providing a structured solution for analysing software citations in academic literature. The paper provides a detailed description of our approach, demonstrating how using GLMs in a single-choice QA paradigm can greatly enhance IE methodologies. Our participation in the SOMD shared task highlights the importance of precise software citation practices and showcases our system's ability to overcome the challenges of disambiguating and extracting relationships between software mentions. This sets the groundwork for future research and development in this field.

Keywords

Cite

@article{arxiv.2404.05587,
  title  = {Enhancing Software-Related Information Extraction via Single-Choice Question Answering with Large Language Models},
  author = {Wolfgang Otto and Sharmila Upadhyaya and Stefan Dietze},
  journal= {arXiv preprint arXiv:2404.05587},
  year   = {2024}
}

Comments

Accepted at: 1st Workshop on Natural Scientific Language Processing and Research Knowledge Graphs (NSLP 2024) Co-located with Extended Semantic Web Conference (ESWC 2024)

R2 v1 2026-06-28T15:47:38.450Z