Papers by Pavel Pecina
Defending Compositionality in Emergent Languages (2022.naacl-srw)
Copied to clipboard
| Challenge: | a recent paper has suggested that compositionality is a key factor in language productivity, but some research has questioned this. |
| Approach: | They argue that compositionality is essential for successful generalization . they run a two-agent communication game to test this hypothesis . |
| Outcome: | The proposed results show that ANNs can generalize well even without compositional behavior . authors argue that the results are incomplete and weak . |
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. |
Document Translation vs. Query Translation for Cross-Lingual Information Retrieval in the Medical Domain (2020.acl-main)
Copied to clipboard
| Challenge: | Existing studies of document translation and query translation are outdated and do not reflect the current advances in machine translation. |
| Approach: | They compare document translation and query translation approaches to cross-lingual information retrieval . they exploit Statistical Machine Translation and Neural Machine Translation paradigms to translate queries into English and English . |
| Outcome: | The proposed approach outperforms the DT approach in translation quality and retrieval quality. |