Papers by Kapil Thadani
Unsupervised Neologism Normalization Using Embedding Space Mapping (D19-55)
Copied to clipboard
| Challenge: | Neologisms refer to recent expressions that are specific to certain entities or events, but have not yet been accepted into mainstream language. |
| Approach: | They propose an unsupervised approach for detecting and normalizing neologisms in social media content without relying on parallel training data. |
| Outcome: | The proposed method detects neologisms and normalizes them to canonical words without training data. |
Effective Few-Shot Classification with Transfer Learning (2020.coling-main)
Copied to clipboard
| Challenge: | Recent work on few-shot learning addresses the problem of learning based on a small amount of training data. |
| Approach: | They adapt the Amazon Review Sentiment Classification (ARSC) text dataset for few-shot learning . they train a single binary classifier to learn all few- shot classes jointly . |
| Outcome: | The proposed approach outperforms most published results on the ARSC text dataset . the results suggest that the classes in the AR SC few-shot task are very similar to each other . |