Not Enough Labeled Data? Just Add Semantics: A Data-Efficient Method for Inferring Online Health Texts

TL;DR

This paper introduces a semantic graph-based approach using Abstract Meaning Representation (AMR) to enhance low-resource health NLP tasks, improving performance on complex texts by augmenting embeddings with semantic information.

Contribution

The study demonstrates that incorporating AMR graphs into NLP models improves performance on low-resource health tasks and handles complex texts better than traditional methods.

Findings

AMR augmentation improves task performance

Semantic graphs help model complex health texts

Models show less variance with complex inputs

Abstract

User-generated texts available on the web and social platforms are often long and semantically challenging, making them difficult to annotate. Obtaining human annotation becomes increasingly difficult as problem domains become more specialized. For example, many health NLP problems require domain experts to be a part of the annotation pipeline. Thus, it is crucial that we develop low-resource NLP solutions able to work with this set of limited-data problems. In this study, we employ Abstract Meaning Representation (AMR) graphs as a means to model low-resource Health NLP tasks sourced from various online health resources and communities. AMRs are well suited to model online health texts as they can represent multi-sentence inputs, abstract away from complex terminology, and model long-distance relationships between co-referring tokens. AMRs thus improve the ability of pre-trained language models to reason about high-complexity texts. Our experiments show that we can improve performance on 6 low-resource health NLP tasks by augmenting text embeddings with semantic graph embeddings. Our approach is task agnostic and easy to merge into any standard text classification pipeline. We experimentally validate that AMRs are useful in the modeling of complex texts by analyzing performance through the lens of two textual complexity measures: the Flesch Kincaid Reading Level and Syntactic Complexity. Our error analysis shows that AMR-infused language models perform better on complex texts and generally show less predictive variance in the presence of changing complexity.