Papers by Mateusz Krubiński
Towards Unified Uni- and Multi-modal News Headline Generation (2024.findings-eacl)
Copied to clipboard
| Challenge: | Current approaches to multimodal summarization and headline generation are limited by hierarchical cross-modal encoders and modality-specific decoders. |
| Approach: | They propose a task formulation that utilizes a simple encoder-decoder model to generate headlines from uni- and multimodal news articles. |
| Outcome: | The proposed model is trained on data of several modalities and extends the decoder to handle the multimodal output. |
MLASK: Multimodal Summarization of Video-based News Articles (2023.findings-eacl)
Copied to clipboard
| Challenge: | Recent studies on multimodal summarization have shown that the benefits of pre-training and using additional modalities in the input are not orthogonal. |
| Approach: | They propose to use a dataset to train a multimodal article summarization model by automatically crawling several news websites. |
| Outcome: | The proposed dataset can be used to model multimodal summarization by training a Transformer-based neural model. |