Papers with multi-encoding and decoding of two sentences

1 papers
Evaluating Discourse Phenomena in Neural Machine Translation (N18-1)

Copied to clipboard

Challenge: Existing models for machine translation have been evaluated with standard automatic metrics, but are poorly adapted to evaluating discourse phenomena.
Approach: They propose to use BLEU to train multi-encoder NMT models on English subtitles to test their ability to exploit previous source and target sentences.
Outcome: The proposed multi-encoder models give limited improvements on the coreference and coherence tests.

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