Papers with representation learning models
System 1 + System 2 = Better World: Neural-Symbolic Chain of Logic Reasoning (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Current NLP models require more than the ability to learn informative representations from data for logic tasks. |
| Approach: | They propose an architecture that explicitly conducts neural logic reasoning on top of the representation learning models. |
| Outcome: | The proposed architecture improves on the commonsense knowledge graph completion task on a commonsensible task with the two-system architecture. |
Pivot Based Language Modeling for Improved Neural Domain Adaptation (N18-1)
Copied to clipboard
| Challenge: | Existing work on domain adaptation does not exploit the structure of the input text . PBLM can naturally feed structure aware text classifiers such as LSTM and CNN . |
| Approach: | They propose a model that integrates pivot-based and NN modeling in a structure aware manner. |
| Outcome: | The proposed model can naturally feed structure aware text classifiers such as LSTM and CNN. |
Autoencoding Keyword Correlation Graph for Document Clustering (2020.acl-main)
Copied to clipboard
| Challenge: | Existing representation learning models do not capture the intra-sentential and inter-sententential features of long-text. |
| Approach: | They propose a graph-based representation for document clustering that builds a Graph Autoencoder on a Keyword Correlation Graph. |
| Outcome: | The proposed graph autoencoder can achieve better clustering performance than existing features. |
On The Performance of Time-Pooling Strategies for End-to-End Spoken Language Identification (2020.lrec-1)
Copied to clipboard
| Challenge: | Language identification (LID) from speech is commonly tackled using similar approaches to those employed for speaker verification/recognition. |
| Approach: | They propose to combine local descriptors and global descriptores into a single global description that can be used for downstream classification tasks. |
| Outcome: | The proposed methods outperform well-known benchmark systems and previously results based on attention only. |
Text Classification Using Label Names Only: A Language Model Self-Training Approach (2020.emnlp-main)
Copied to clipboard
| Challenge: | Current text classification methods require a large number of labeled documents as training data. |
| Approach: | They propose a model that uses only the label name of each class to train classification models on unlabeled data without using any labeled examples. |
| Outcome: | The proposed model achieves 90% accuracy on four benchmark datasets using label names as the only supervision . |