Papers with multilingual method

2 papers
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.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations