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

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

18 Oct 2019IJCNLP 2019 11arXiv:1910.08435archive 2025-07-28

Angela Fan, Claire Gardent, Chloe Braud, Antoine Bordes

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 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.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

denisewong1/ASX300 mentioned on GitHubtf report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Document SummarizationLong Form Question AnsweringMulti-Document SummarizationOpen-Domain Question AnsweringQuestion Answeringgraph construction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Open-Domain Question Answering ELI5 E-MCA Rouge-1 30.0 #4 of 6 Archive leaderboard report
Open-Domain Question Answering ELI5 E-MCA Rouge-2 5.8 #4 of 6 Archive leaderboard report
Open-Domain Question Answering ELI5 E-MCA Rouge-L 24.0 #4 of 6 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections