LLM-RM at SemEval-2023 Task 2: Multilingual Complex NER using XLM-RoBERTa

TL;DR

This paper presents a multilingual approach to complex named entity recognition by fine-tuning XLM-RoBERTa on datasets across 12 languages for the SemEval-2023 Task 2 challenge.

Contribution

It introduces a cross-lingual fine-tuning method using XLM-RoBERTa for multilingual complex NER in 12 languages, addressing the challenge of recognizing complex entities.

Findings

Achieved competitive results in SemEval-2023 Task 2

Demonstrated effectiveness of cross-lingual transfer learning

Improved NER performance across multiple languages

Abstract

Named Entity Recognition(NER) is a task of recognizing entities at a token level in a sentence. This paper focuses on solving NER tasks in a multilingual setting for complex named entities. Our team, LLM-RM participated in the recently organized SemEval 2023 task, Task 2: MultiCoNER II,Multilingual Complex Named Entity Recognition. We approach the problem by leveraging cross-lingual representation provided by fine-tuning XLM-Roberta base model on datasets of all of the 12 languages provided -- Bangla, Chinese, English, Farsi, French, German, Hindi, Italian, Portuguese, Spanish, Swedish and Ukrainian