Recently, pre-trained language representation models such as BERT and RoBERTa have achieved significant results in a wide range of natural language processing (NLP) tasks, however, it requires extremely high computational cost. Curriculum Learning (C
L) is one of the potential solutions to alleviate this problem. CL is a training strategy where training samples are given to models in a meaningful order instead of random sampling. In this work, we propose a new CL method which gradually increases the block-size of input text for training the self-attention mechanism of BERT and its variants using the maximum available batch-size. Experiments in low-resource settings show that our approach outperforms the baseline in terms of convergence speed and final performance on downstream tasks.
Different linearizations have been proposed to cast dependency parsing as sequence labeling and solve the task as: (i) a head selection problem, (ii) finding a representation of the token arcs as bracket strings, or (iii) associating partial transiti
on sequences of a transition-based parser to words. Yet, there is little understanding about how these linearizations behave in low-resource setups. Here, we first study their data efficiency, simulating data-restricted setups from a diverse set of rich-resource treebanks. Second, we test whether such differences manifest in truly low-resource setups. The results show that head selection encodings are more data-efficient and perform better in an ideal (gold) framework, but that such advantage greatly vanishes in favour of bracketing formats when the running setup resembles a real-world low-resource configuration.
