Papers with Neural encoder-decoder models
MEMD: A Diversity-Promoting Learning Framework for Short-Text Conversation (C18-1)
Copied to clipboard
| Challenge: | Neural encoder-decoder models tend to generate meaningless and generic responses regardless of what the input text is. |
| Approach: | They propose an easy-to-extend learning framework based on latent vectors to provide training guidance without resorting to extra data or complicating network’s inner structure. |
| Outcome: | The proposed framework improves the quality of generated responses according to automatic metrics and human evaluations, yielding more diverse and smooth replies. |
Positional Encoding to Control Output Sequence Length (N19-1)
Copied to clipboard
| Challenge: | Neural encoder-decoder models have been successful in natural language generation tasks, but they must be limited to a specified length for abstractive summarization. |
| Approach: | They propose a sinusoidal positional extension to preserve the length constraint so that a neural encoder-decoder model can generate a text of any length even if the target length is unseen in training data. |
| Outcome: | The proposed method can generate a text of any length even if the target length is unseen in training data and improves ROUGE scores. |