Papers by Sophie Fellenz
Tethering Broken Themes: Aligning Neural Topic Models with Labels and Authors (2025.findings-naacl)
Copied to clipboard
| Challenge: | Recent studies suggest that topic models do not align well with human intentions. |
| Approach: | They propose a method to align neural topic models with both labels and authorship information. |
| Outcome: | The proposed method improves existing models in terms of topic quality and alignment. |
Continual Neural Topic Model (2026.eacl-long)
Copied to clipboard
| Challenge: | Continual Neural Topic Models (CoNTMs) learn topic models at subsequent time steps without forgetting what was previously learned. |
| Approach: | They propose a Continual Neural Topic Model which continuously learns topic models at subsequent time steps without forgetting what was previously learned. |
| Outcome: | The proposed model outperforms the dynamic topic model in topic quality and predictive perplexity while being able to capture topic changes online. |
A Call for Standardization and Validation of Text Style Transfer Evaluation (2023.findings-acl)
Copied to clipboard
| Challenge: | Text style transfer (TST) evaluation is inconsistent in practice. |
| Approach: | They conduct a meta-analysis on human and automated TST evaluation and experimentation . they find a standardization gap and a validation gap in the field . |
| Outcome: | The authors find that evaluation procedures are inconsistent and that they need to improve on them. |
Characterizing Text Datasets with Psycholinguistic Features (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing algorithms for fine-tuning language models on task-specific data are not optimal for all scenarios. |
| Approach: | They propose a framework to fine-tune text models on task-specific data using meta-datasets. |
| Outcome: | The proposed framework evaluates multiple dimensions of text and discourse, producing interpretable, low-dimensional embeddings. |
Text Style Transfer Evaluation Using Large Language Models (2024.lrec-main)
Copied to clipboard
| Challenge: | Recent advances in large language models (LLMs) have demonstrated their capacity to match and even exceed average human performance across diverse, unseen tasks. |
| Approach: | They compare the results of different LLMs in TST evaluation using multiple input prompts and introduce the concept of prompt ensembling. |
| Outcome: | The proposed model outperforms human evaluations on multiple input prompts. |
Evaluating Dynamic Topic Models (2024.acl-long)
Copied to clipboard
| Challenge: | Existing evaluation measures to evaluate the progression of topics in dynamic topic models (DTMs) are difficult due to their unsupervised nature, but are crucial for detecting trends in time-indexed documents. |
| Approach: | They propose to combine topic quality and temporal consistency to evaluate the progression of topics over time in dynamic topic models. |
| Outcome: | The proposed measure correlates well with human judgment and can be used to identify changing topics and evaluate different models and LLMs. |