5 papers with code • 1 benchmarks • 0 datasets
In particular, we obtain the augmented semantic information from a large-scale corpus, and propose an attentive semantic augmentation module and a gate module to encode and aggregate such information, respectively.
Ranked #2 on Named Entity Recognition on WNUT 2016
Traditional methods for deep NLG adopt pipeline approaches comprising stages such as constructing syntactic input, predicting function words, linearizing the syntactic input and generating the surface forms.
Ranked #1 on Data-to-Text Generation on SR11Deep
Our novel approach provides a summary that represents the most relevant aspects of a news item that users comment on, incorporating the social context as a source of information to summarize texts in online social networks.
Ranked #1 on on Emol news articles dataset