Papers by Anton Eklund
PromptStream: Self-Supervised News Story Discovery Using Topic-Aware Article Representations (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing methods for news story discovery relied on sparse document representations such as keywords and TF-IDF vectors. |
| Approach: | They propose a method that constructs article embeddings using cloze-style prompting and self-supervised contrastive learning techniques to tackle this task. |
| Outcome: | The proposed model is able to identify coherent news stories within a news stream and to monitor their progress. |
Topic Modeling by Clustering Language Model Embeddings: Human Validation on an Industry Dataset (2022.emnlp-industry)
Copied to clipboard
| Challenge: | Topic models are powerful tools to get overview of large collections of text data. |
| Approach: | They propose to use a tool called STELLAR for interactive topic browsing to evaluate topics from a real-world dataset. |
| Outcome: | The proposed model performs better than LDA models in the real-world and is scalable. |
Dynamic Topic Modeling by Clustering Embeddings from Pretrained Language Models: A Research Proposal (2022.aacl-srw)
Copied to clipboard
| Challenge: | Neural Topic Models (NTMs) are topic models that are created with the help of a pretrained language model. |
| Approach: | They propose to do Neural Topic Modeling by Clustering document Embeddings (NTM-CE) with a pretrained language model to create dynamic topic models. |
| Outcome: | The proposed model can be evaluated theoretically and practically using quantitative measurements of coherence and human evaluation to evaluate the model. |