Papers by Jean Baptiste Faddoul
Efficient Pointwise-Pairwise Learning-to-Rank for News Recommendation (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Recent work leverages the power of pretrained language models to rank news items . pointwise approaches fail to capture comparative information between items that is more effective for ranking tasks. |
| Approach: | They propose a framework for PLM-based news recommendation that integrates pointwise relevance prediction and pairwise comparisons in a scalable manner. |
| Outcome: | The proposed framework outperforms state-of-the-art methods on the MIND and Adressa news recommendation datasets. |
Chargrid: Towards Understanding 2D Documents (D18-1)
Copied to clipboard
Anoop R Katti, Christian Reisswig, Cordula Guder, Sebastian Brarda, Steffen Bickel, Johannes Höhne, Jean Baptiste Faddoul
| Challenge: | a novel type of text representation preserves the 2D layout of a document . a computer vision algorithm that extracts text from image is not optimal for understanding semantics . |
| Approach: | They propose a new type of text representation that preserves the 2D layout of a document . they demonstrate that it significantly outperforms approaches based on sequential text or document images . |
| Outcome: | The proposed approach outperforms approaches based on sequential text or document images on an information extraction task from invoices. |