Architectural Sweet Spots for Modeling Human Label Variation by the Example of Argument Quality: It’s Best to Relate Perspectives!
Submission Type: Regular Long Paper
Submission Track: Sentiment Analysis, Stylistic Analysis, and Argument Mining
Submission Track 2: Human-Centered NLP
Keywords: argument quality, perspectivism, inter-annotator-disagreement, LLM, recommender, argument mining
TL;DR: Argument quality can not reduce to a single majority label but has to decompose into different perspectives - we explore different model architectures to capture the interaction between individual views and common ground.
Abstract: Many annotation tasks in natural language processing are highly subjective in that there can be different valid and justified perspectives on what is a proper label for a given example.
This also applies to the judgment of argument quality, where the assignment of a single ground truth is often questionable.
At the same time, there are generally accepted concepts behind argumentation that form a common ground.
To best represent the interplay of individual and shared perspectives, we consider a continuum of approaches ranging from models that fully aggregate perspectives into a majority label to ``share nothing''-architectures in which each annotator is considered in isolation from all other annotators.
In between these extremes, inspired by models used in the field of recommender systems, we investigate the extent to which architectures that predict labels for single annotators but include layers that model the relations between different annotators are beneficial.
By means of two tasks of argument quality classification (argument concreteness and validity/novelty of conclusions), we show that recommender architectures increase the averaged annotator-individual F1-scores up to 43% over a majority-label model.
Our findings indicate that approaches to subjectivity can benefit from relating individual perspectives.
Submission Number: 3743
Loading