Skip to Main content Skip to Navigation
Conference papers

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

Abstract : Query-based open-domain NLP tasks require information synthesis from long and diverse web results. Current approaches extrac-tively 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 web search information and reduces redundancy. We show that by linearizing the graph into a structured input sequence, models can encode the graph representations within a standard Sequence-to-Sequence setting. For two generative tasks with very long text input , long-form question answering and multi-document summarization, feeding graph representations as input can achieve better performance than using retrieved text portions.
Document type :
Conference papers
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-02277063
Contributor : Claire Gardent <>
Submitted on : Tuesday, September 3, 2019 - 1:10:09 PM
Last modification on : Wednesday, October 21, 2020 - 5:12:04 PM
Long-term archiving on: : Wednesday, February 5, 2020 - 10:29:58 PM

File

output.pdf
Files produced by the author(s)

Licence


Public Domain

Identifiers

Citation

Angela Fan, Claire Gardent, Chloé Braud, Antoine Bordes. Using Local Knowledge Graph Construction to Scale Seq2Seq Models to Multi-Document Inputs. 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing, Nov 2019, Hong Kong, China. ⟨10.18653/v1/D19-1428⟩. ⟨hal-02277063⟩

Share

Metrics

Record views

286

Files downloads

782