Titlebook: Natural Language Processing and Information Systems; 29th International C Amon Rapp,Luigi Di Caro,Vijayan Sugumaran Conference proceedings

鳥場

書目名稱Natural Language Processing and Information Systems影響因子(影響力)




書目名稱Natural Language Processing and Information Systems影響因子(影響力)學科排名




書目名稱Natural Language Processing and Information Systems網(wǎng)絡(luò)公開度




書目名稱Natural Language Processing and Information Systems網(wǎng)絡(luò)公開度學科排名




書目名稱Natural Language Processing and Information Systems被引頻次




書目名稱Natural Language Processing and Information Systems被引頻次學科排名




書目名稱Natural Language Processing and Information Systems年度引用




書目名稱Natural Language Processing and Information Systems年度引用學科排名




書目名稱Natural Language Processing and Information Systems讀者反饋




書目名稱Natural Language Processing and Information Systems讀者反饋學科排名

心神不寧

說笑

減至最低

石墨

,The Influence of?Iconicity in?Transfer Learning for?Sign Language Recognition,Perceptron architecture and the temporal information with a Gated Recurrent Unit. Experimental results showed a 7.02% improvement for Arabic and 1.07% for Flemish when conducting iconic TL from Chinese and Greek respectively.

MOTTO

背帶

,Semi-supervised Named Entity Recognition for?Low-Resource Languages Using Dual PLMs,eriments using seven low-resource, but widely spoken African languages, demonstrating that augmented datasets generated by our approach achieve better results in six out of the seven languages. Furthermore, we conduct cross-lingual zero-shot experiments between language pairs and multi-lingual experiments to validate the robustness of our method.

蛤肉

,Grounding Toxicity in?Real-World Events Across Languages,fferent events and language communities, showing that toxicity is a complex phenomenon in which many different factors interact and still need to be investigated. We released the data and code for further research (.).

有機體

Adaptive Greedy Layer Pruning: Iterative Layer Pruning with Subsequent Model Repurposing,ious degradation of task performance. Indeed, we were able to omit up to 2.2x more layers from the investigated PLMs (depending on the backbone model) compared to a strong layer pruning baseline when preserving no less than 95% of the performance of the full backbone model.

合法