Latent Space Interpretation for Stylistic Analysis and Explainable Authorship Attribution
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866929496465080320 |
|---|---|
| author | Alshomary, Milad Ri, Narutatsu Apidianaki, Marianna Patel, Ajay Muresan, Smaranda McKeown, Kathleen |
| author_facet | Alshomary, Milad Ri, Narutatsu Apidianaki, Marianna Patel, Ajay Muresan, Smaranda McKeown, Kathleen |
| contents | Recent state-of-the-art authorship attribution methods learn authorship representations of texts in a latent, non-interpretable space, hindering their usability in real-world applications. Our work proposes a novel approach to interpreting these learned embeddings by identifying representative points in the latent space and utilizing LLMs to generate informative natural language descriptions of the writing style of each point. We evaluate the alignment of our interpretable space with the latent one and find that it achieves the best prediction agreement compared to other baselines. Additionally, we conduct a human evaluation to assess the quality of these style descriptions, validating their utility as explanations for the latent space. Finally, we investigate whether human performance on the challenging AA task improves when aided by our system's explanations, finding an average improvement of around +20% in accuracy. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_07072 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Latent Space Interpretation for Stylistic Analysis and Explainable Authorship Attribution Alshomary, Milad Ri, Narutatsu Apidianaki, Marianna Patel, Ajay Muresan, Smaranda McKeown, Kathleen Computation and Language Recent state-of-the-art authorship attribution methods learn authorship representations of texts in a latent, non-interpretable space, hindering their usability in real-world applications. Our work proposes a novel approach to interpreting these learned embeddings by identifying representative points in the latent space and utilizing LLMs to generate informative natural language descriptions of the writing style of each point. We evaluate the alignment of our interpretable space with the latent one and find that it achieves the best prediction agreement compared to other baselines. Additionally, we conduct a human evaluation to assess the quality of these style descriptions, validating their utility as explanations for the latent space. Finally, we investigate whether human performance on the challenging AA task improves when aided by our system's explanations, finding an average improvement of around +20% in accuracy. |
| title | Latent Space Interpretation for Stylistic Analysis and Explainable Authorship Attribution |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2409.07072 |