Papers by Amirmohammad Rooshenas
Training Structured Prediction Energy Networks with Indirect Supervision (N18-2)
Copied to clipboard
| Challenge: | a new rank-based training method for structured prediction energy networks is proposed . structured prediction is important in many domains, including computer vision, computational biology and natural language processing. |
| Approach: | They propose a rank-based training method for structured prediction energy networks . they use a scoring function defined with domain knowledge to train the models . |
| Outcome: | The proposed method minimizes ranking violation of the sampled structures with respect to a scalar scoring function defined with domain knowledge. |
Energy-Based Reranking: Improving Neural Machine Translation Using Energy-Based Models (2021.acl-long)
Copied to clipboard
Sumanta Bhattacharyya, Amirmohammad Rooshenas, Subhajit Naskar, Simeng Sun, Mohit Iyyer, Andrew McCallum
| Challenge: | Autoregressive neural machine translation (NMT) uses a tractable likelihood computation and efficient sampling. |
| Approach: | They propose to use an energy-based model to mimic the behavior of the task measure and use it to train an energy based re-ranking algorithm. |
| Outcome: | The proposed model improves on the samples drawn from the NMT with a higher BLEU score than the experimental model and the energy-based re-ranking algorithm. |