1 |
Continual Mixed-Language Pre-Training for Extremely Low-Resource Neural Machine Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
BiToD: A Bilingual Multi-Domain Dataset For Task-Oriented Dialogue Modeling ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Adapting High-resource NMT Models to Translate Low-resource Related Languages without Parallel Data ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Learning Fast Adaptation on Cross-Accented Speech Recognition ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
Exploring Fine-tuning Techniques for Pre-trained Cross-lingual Models via Continual Learning ...
|
|
|
|
Abstract:
Recently, fine-tuning pre-trained language models (e.g., multilingual BERT) to downstream cross-lingual tasks has shown promising results. However, the fine-tuning process inevitably changes the parameters of the pre-trained model and weakens its cross-lingual ability, which leads to sub-optimal performance. To alleviate this problem, we leverage continual learning to preserve the original cross-lingual ability of the pre-trained model when we fine-tune it to downstream tasks. The experimental result shows that our fine-tuning methods can better preserve the cross-lingual ability of the pre-trained model in a sentence retrieval task. Our methods also achieve better performance than other fine-tuning baselines on the zero-shot cross-lingual part-of-speech tagging and named entity recognition tasks. ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences; Machine Learning cs.LG
|
|
URL: https://arxiv.org/abs/2004.14218 https://dx.doi.org/10.48550/arxiv.2004.14218
|
|
BASE
|
|
Hide details
|
|
9 |
Meta-Transfer Learning for Code-Switched Speech Recognition ...
|
|
|
|
BASE
|
|
Show details
|
|
10 |
On the Importance of Word Order Information in Cross-lingual Sequence Labeling ...
|
|
|
|
BASE
|
|
Show details
|
|
11 |
Attention-Informed Mixed-Language Training for Zero-shot Cross-lingual Task-oriented Dialogue Systems ...
|
|
|
|
BASE
|
|
Show details
|
|
12 |
Zero-shot Cross-lingual Dialogue Systems with Transferable Latent Variables ...
|
|
|
|
BASE
|
|
Show details
|
|
13 |
Towards Universal End-to-End Affect Recognition from Multilingual Speech by ConvNets ...
|
|
|
|
BASE
|
|
Show details
|
|
14 |
Code-Switched Language Models Using Neural Based Synthetic Data from Parallel Sentences ...
|
|
|
|
BASE
|
|
Show details
|
|
15 |
Hierarchical Meta-Embeddings for Code-Switching Named Entity Recognition ...
|
|
|
|
BASE
|
|
Show details
|
|
16 |
GlobalTrait: Personality Alignment of Multilingual Word Embeddings ...
|
|
|
|
BASE
|
|
Show details
|
|
17 |
Learn to Code-Switch: Data Augmentation using Copy Mechanism on Language Modeling ...
|
|
|
|
BASE
|
|
Show details
|
|
18 |
Mem2Seq: Effectively Incorporating Knowledge Bases into End-to-End Task-Oriented Dialog Systems ...
|
|
|
|
BASE
|
|
Show details
|
|
19 |
Bilingual Character Representation for Efficiently Addressing Out-of-Vocabulary Words in Code-Switching Named Entity Recognition ...
|
|
|
|
BASE
|
|
Show details
|
|
20 |
Code-Switching Language Modeling using Syntax-Aware Multi-Task Learning ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|