Adversarial Training for Commonsense Inference
| Autor: | Lis Pereira, Fei Cheng, Ichiro Kobayashi, Masayuki Asahara, Xiaodong Liu |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
FOS: Computer and information sciences
Computer Science - Computation and Language business.industry Computer science Training (meteorology) Inference 02 engineering and technology Machine learning computer.software_genre Adversarial system Reading comprehension 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Artificial intelligence business computer Computation and Language (cs.CL) Word (computer architecture) |
| Zdroj: | RepL4NLP@ACL |
| Popis: | application/pdf Ochanomizu University Microsoft Research Kyoto University National Institute for Japanese Language and Linguistics We propose an AdversariaL training algorithm for commonsense InferenCE (ALICE). We apply small perturbations to word embeddings and minimize the resultant adversarial risk to regularize the model. We exploit a novel combination of two different approaches to estimate these perturbations: 1) using the true label and 2) using the model prediction. Without relying on any human-crafted features, knowledge bases, or additional datasets other than the target datasets, our model boosts the fine-tuning performance of RoBERTa, achieving competitive results on multiple reading comprehension datasets that require commonsense inference. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|