Papers with Deep Neural Network
DNN-driven Gradual Machine Learning for Aspect-term Sentiment Analysis (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for Aspect-Term Sentiment Analysis (ATSA) use pre-specified lexicons to extract sentiment features. |
| Approach: | They propose a Deep Neural Network-driven approach for Aspect-Term Sentiment Analysis (ATSA) that leverages shared features between labeled and unlabeled instances for knowledge conveyance. |
| Outcome: | The proposed approach consistently achieves state-of-the-art performance on real benchmark data. |
FAtNet: Cost-Effective Approach Towards Mitigating the Linguistic Bias in Speaker Verification Systems (2022.findings-naacl)
Copied to clipboard
| Challenge: | Linguistic bias in Deep Neural Network (DNN) based systems is a critical challenge that needs attention. |
| Approach: | They propose to integrate a lightweight embedding with existing NLP systems to mitigate linguistic bias without adaptation. |
| Outcome: | The proposed framework reduces linguistic bias and enhances usability of baselines for twelve languages. |
Transfer Learning for Text Classification via Model Risk Analysis (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing approaches to text classification are limited by distribution drift and misprediction risk. |
| Approach: | They propose a model risk analysis approach to adapt a pre-trained DNN model to a new dataset given only a small set of representative data. |
| Outcome: | The proposed model performs considerably better than existing approaches on real datasets. |
Deep Dominance - How to Properly Compare Deep Neural Models (P19-1)
Copied to clipboard
| Challenge: | Existing methods for comparing DNNs on unseen data are not suitable for this task. |
| Approach: | They propose to adapt a test for the Almost Stochastic Dominance relation between two distributions to the problem by comparing their performance on unseen data. |
| Outcome: | The proposed method meets all criteria while previously proposed methods fail to do so. |
Lexical Tone Recognition in Mizo using Acoustic-Prosodic Features (2020.lrec-1)
Copied to clipboard
| Challenge: | Mizo is an under-studied Tibeto-Burman tonal language of the Northeast of India. |
| Approach: | They propose to use acoustic-prosodic parameters to automatically recognize four phonological tones in Mizo using a set of features computed from Fundamental Frequency contours. |
| Outcome: | The proposed model performs better than the existing classifiers in recognizing four phonological tones in Mizo using acoustic-prosodic parameters. |