A Comprehensive Study on Attention-Based NER

Islam, Tanvir; Zinat, Sakila Mahbin; Sukhi, Shamima; Mridha, M. F.

doi:10.1007/978-981-16-2597-8_57

Cited by 3 publications

(1 citation statement)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another approach in NER, which is mentioned in Islam et al (2022), consists of using an attention mechanism to minimize the problem of detecting redundant and inessential data and ignoring them entirely. Combining semantic, glyph, and phonetic features to improve the expression ability of Chinese character embedding, Li and Meng (2021) proposes an architecture based on Fusion Embedding for the Chinese language.…”

Section: Introductionmentioning

confidence: 99%

MarSan at SemEval-2022 Task 11: Multilingual complex named entity recognition using T5 and transformer encoder

Tavan¹,

Najafi²

2022

Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)

View full text Add to dashboard Cite

The multilingual complex named entity recognition task of SemEval2020 required participants to detect semantically ambiguous and complex entities in 11 languages. In order to participate in this competition, a deep learning model is being used with the T5 text-to-text language model and its multilingual version, MT5, along with the transformer's encoder module. The subtoken check has also been introduced, resulting in a 4% increase in the model F1score in English. We also examined the use of the BPEmb model for converting input tokens to representation vectors in this research. A performance evaluation of the proposed entity detection model is presented at the end of this paper. Six different scenarios were defined, and the proposed model was evaluated in each scenario within the English development set. Our model is also evaluated in other languages.

show abstract

Section: Introductionmentioning

confidence: 99%