Papers with multilingual method
Multilingual Normalization of Temporal Expressions with Masked Language Models (2023.eacl-main)
Copied to clipboard
| Challenge: | Existing methods for normalizing temporal expressions are rule-based, which severely limits the applicability in multilingual settings. |
| Approach: | They propose a neural method for normalizing temporal expressions based on masked language modeling and a slot-based prediction scheme for context-independent representations. |
| Outcome: | The proposed method outperforms existing rule-based methods in many languages and in particular, for low-resource languages with performance improvements of up to 33 F1 on average compared to the state of the art. |
Unveiling the Power of Integration: Block Diagram Summarization through Local-Global Fusion (2024.findings-acl)
Copied to clipboard
| Challenge: | Document Artificial Intelligence (Document AI) is gaining momentum across industries for streamlining document processes, enhancing efficiency, and extracting insights from unstructured data. |
| Approach: | They propose a fusion framework that summarizes block diagrams by integrating local and global information, catering to both English and Korean languages. |
| Outcome: | The proposed framework surpasses all previous methods and models for block diagram summarization on a dataset of BD-EnKo in English and Korean. |