Papers with convolutional models
Adaptive Convolution for Multi-Relational Learning (N19-1)
Copied to clipboard
| Challenge: | Existing convolutional neural networks fail to model full interactions between entities and relations, which limits the performance of link prediction. |
| Approach: | They propose a convolutional network that maximizes entity-relation interactions in a convergent fashion. |
| Outcome: | The proposed convolutional network performs better than baseline models on multiple datasets. |
Learning Better Internal Structure of Words for Sequence Labeling (D18-1)
Copied to clipboard
| Challenge: | a gap exists between methods for learning representations of sentences and words . authors propose a convolutional neural architecture with no down-sampling for learning words based on character embeddings . |
| Approach: | They propose a funnel-shaped wide convolutional neural architecture with no down-sampling for learning words' internal structure. |
| Outcome: | The proposed model outperforms other character embedding models on six sequence labeling datasets. |
Are Pretrained Convolutions Better than Pretrained Transformers? (2021.acl-long)
Copied to clipboard
| Challenge: | Recent research has shown promise in entirely convolutional, or CNN, architectures, but they have not been explored using the pre-train-fine-tune paradigm. |
| Approach: | They propose to use the pre-train-fine-tune paradigm to study convolutional models. |
| Outcome: | The proposed architectures outperform Transformers in certain scenarios, but with caveats. |
Training Deeper Neural Machine Translation Models with Transparent Attention (D18-1)
Copied to clipboard
| Challenge: | Existing NMT models are shallow in comparison to convolutional models used for both text and vision tasks. |
| Approach: | They propose to modify the attention mechanism to ease the optimization of deeper models by a simple modification to the seq2seq with attention paradigm. |
| Outcome: | The proposed model achieves consistent gains of 0.7-1.1 BLEU on the benchmark WMT’14 English-German and WMT'15 Czech-English tasks. |
Simple Recurrent Units for Highly Parallelizable Recurrence (D18-1)
Copied to clipboard
| Challenge: | recurrent neural networks scale poorly due to the intrinsic difficulty in parallelizing their state computations. |
| Approach: | They propose a simple recurrent unit that provides expressive recurrence and allows highly parallel implementation. |
| Outcome: | The proposed model achieves 5—9x speed-up over cuDNN-optimized LSTM on classification and question answering datasets and delivers stronger results than LS and convolutional models. |