Large Transformer-based models were shown to be reducible to a smaller number of selfattention heads and layers. We consider this phenomenon from the perspective of the lottery ticket hypothesis, using both structured and magnitude pruning. For fine-tuned BERT, we show that (a) it is possible to find subnetworks achieving performance that is comparable with that of the full model, and (b) similarly-sized subnetworks sampled from the rest of the model perform worse. Strikingly, with structured pruning even the worst possible subnetworks remain highly trainable, indicating that most pre-trained BERT weights are potentially useful. We also study the "good" subnetworks to see if their success can be attributed to superior linguistic knowledge, but find them unstable, and not explained by meaningful self-attention patterns.

Much of the recent success in NLP is due to the large Transformer-based models such as BERT (Devlin et al, 2019). However, these models have been shown to be reducible to a smaller number of self-attention heads and layers. We consider this phenomenon from the perspective of the lottery ticket hypothesis. For fine-tuned BERT, we show that (a) it is possible to find a subnetwork of elements that achieves performance comparable with that of the full model, and (b) similarly-sized subnetworks sampled from the rest of the model perform worse. However, the "bad" subnetworks can be fine-tuned separately to achieve only slightly worse performance than the "good" ones, indicating that most weights in the pretrained BERT are potentially useful. We also show that the "good" subnetworks vary considerably across GLUE tasks, opening up the possibilities to learn what knowledge BERT actually uses at inference time.

No abstract

This paper describes our submission for the SemEval-2019 Suggestion Mining task. A simple Convolutional Neural Network (CNN) classifier with contextual word representations from a pre-trained language model is used for sentence classification. The model is trained using tri-training, a semi-supervised bootstrapping mechanism for labelling unseen data. Tri-training proved to be an effective technique to accommodate domain shift for cross-domain suggestion mining (Subtask B) where there is no hand labelled training data. For in-domain evaluation (Subtask A), we use the same technique to augment the training set. Our system ranks thirteenth in Subtask A with an F 1-score of 68.07 and third in Subtask B with an F 1-score of 81.94.

No abstract