Work

Textagon: Boosting Language Models with Theory-guided Parallel Representations

Year: 2025

Type: conference-paper

Abstract: Pretrained language models have significantly advanced the state of the art in generating distributed representations of text.However, they do not account for the wide variety of available expert-generated language resources and lexicons that explicitly encode linguistic/domain knowledge.Such lexicons can be paired with learned embeddings to further enhance NLP prediction and linguistic inquiry.In this work we present Textagon, a Python package for generating parallel representations for text based on predefined lexicons and selecting representations that provide the most information.We discuss the motivation behind the software, its implementation, as well as two case studies for its use to demonstrate operational utility.

Source: Annual Meeting of the Association for Computational Linguistics (ACL)

DOI: 10.18653/v1/2025.acl-demo.9

Authors: John P. Lalor, Ruiyang Qin, David Dobolyi, Ahmed Abbasi

Institutions: University of Notre Dame, Villanova University, University of Colorado Boulder, University of Colorado System

Language: English

Topic: Topic Modeling

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funder: National Science Foundation

Awards: BD Spokes: SPOKE: SOUTH: Large-Scale Medical Informatics for Patient Care Coordination and Engagement, XPS:FULL: New Abstractions and Applications for Automata Computing, III: Small: Collaborative Research: Social Media Based Analysis of Adverse Drug Events: User Modeling, Signal Reliability, and Signal Validation