Layered Insights: Generalizable Analysis of Authorial Style by Leveraging All Transformer Layers
We propose a new approach for the authorship attribution task that leverages the various linguistic representations learned at different layers of pre-trained transformer-based models. We evaluate our approach on three datasets, comparing it to a state-of-the-art baseline in in-domain and out-of-domain scenarios. We found that utilizing various transformer layers improves the robustness of authorship attribution models when tested on out-of-domain data, resulting in new state-of-the-art results. Our analysis gives further insights into how our model's different layers get specialized in representing certain stylistic features that benefit the model when tested out of the domain.
Code (0)
등록된 구현이 없습니다.
Tasks
AllAuthorship AttributionSimilar Papers 제목 키워드 기반
Exploring Narrative Clustering in Large Language Models: A Layerwise Analysis of BERT
This study investigates the internal mechanisms of BERT, a transformer-based large language model, with a focus on its ability to cluster narrative content and authorial style across its layers. Using a dataset of narrat…
ClusteringDimensionality ReductionLanguage ModelingLanguage Modelling+1Personalized Image Generation from an Author Writing Style
Translating nuanced, textually-defined authorial writing styles into compelling visual representations presents a novel challenge in generative AI. This paper introduces a pipeline that leverages Author Writing Sheets (A…
Personalized Image GenerationTraSE: Towards Tackling Authorial Style from a Cognitive Science Perspective
Stylistic analysis of text is a key task in research areas ranging from authorship attribution to forensic analysis and personality profiling. The existing approaches for stylistic analysis are plagued by issues like top…
Authorship AttributionA Supervised Learning Approach Towards Profiling the Preservation of Authorial Style in Literary Translations
Modeling Authorial Style in Urdu Novels Using Character Interaction Graphs and Graph Neural Networks
Authorship analysis has traditionally focused on lexical and stylistic cues within text, while higher-level narrative structure remains underexplored, particularly for low-resource languages such as Urdu. This work propo…