WeGen adds a weakly supervised Relation Guider and dynamic multi-interaction transfer to an encoder-decoder question generator to better use whole-passage context around an answer span.
Sequence to sequence learning with neural networks
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CL 2years
2019 2verdicts
UNVERDICTED 2representative citing papers
Sharing attention weights in adjacent Transformer layers yields 1.3X inference speedup with negligible BLEU loss on ten WMT and NIST tasks.
citing papers explorer
-
Weak Supervision Enhanced Generative Network for Question Generation
WeGen adds a weakly supervised Relation Guider and dynamic multi-interaction transfer to an encoder-decoder question generator to better use whole-passage context around an answer span.
-
Sharing Attention Weights for Fast Transformer
Sharing attention weights in adjacent Transformer layers yields 1.3X inference speedup with negligible BLEU loss on ten WMT and NIST tasks.