Papers with Neural encoder-decoder models

2 papers
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.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations