Papers with annealing schedule
HeLo: Learning-Free Lookahead Decoding for Conversation Infilling (2022.findings-emnlp)
Copied to clipboard
| Challenge: | We propose a scalable decoding strategy for conversation infilling . large pretrained language models are effective solutions to many popular natural language generation tasks such as machine translation and conversational dialogue. |
| Approach: | They propose a heuristic guided lookahead decoding strategy for conversation infilling which leverages a greedy lookalike phase before committing to any token. |
| Outcome: | The proposed strategy outperforms baselines when evaluated with automatic and human evaluation metrics, which, we argue, are appropriate for the task. |