Graph

Because of polysemy, distant labeling for information extraction leads to noisy train- ing data. We describe a procedure for re- ducing this noise by using label propaga- tion on a …...

AbstractKeywords or keyphrases are often used to highlight a document’s domains or main topics. Unsupervised keyphrase extraction (UKE) has always been highly anticipated because no labeled data is needed to …...

AbstractA graph is a suitable data structure to represent the structural information of text. Recently, multi-hop question answering (MHQA) tasks, which require inter-paragraph/sentence linkages, have come to exploit such properties …...