Attention-Weighted Multilingual BERT for Zero-Shot Cross-Lingual Dialogue Slot-Filling

Multilingual BERT (mBERT), a language model pre-trained on large multilingual corpora, has impressive zero-shot cross-lingual transfer capabilities and performs surprisingly well on zero-shot POS tagging and Named Entity Recognition (NER), as well as on cross-lingual model transfer. At present, the mainstream methods to solve the cross-lingual downstream tasks are always using the last transformer layer's output of mBERT as the representation of linguistic information. In this work, we explore the complementary property of lower layers to the last transformer layer of mBERT. A feature aggregat

Research goal: What is the impact of incorporating attention weights from a pre-trained multilingual BERT model on the zero-shot cross-lingual transfer performance of MLT for dialogue slot-filling, measured by F1 scores on the SGD and WoZ benchmarks?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.5/10.