Using Local Knowledge Graph Construction to Scale Seq2Seq Models to Multi-Document Inputs

Claire Gardent
Claire Gardent
Chloé Braud
Chloé Braud

EMNLP/IJCNLP (1), pp. 4184-4194, 2019.

Cited by: 7|Bibtex|Views88|DOI:https://doi.org/10.18653/v1/D19-1428
EI
Other Links: academic.microsoft.com|dblp.uni-trier.de|arxiv.org

Abstract:

Query-based open-domain NLP tasks require information synthesis from long and diverse web results. Current approaches extractively select portions of web text as input to Sequence-to-Sequence models using methods such as TF-IDF ranking. We propose constructing a local graph structured knowledge base for each query, which compresses the ...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments