mlsanityData to 14 Oct 2026

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

arXiv 1910.08435 ↗First posted 18 Oct 2019cs.CLcited by 38

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 38 papers in the map (data through 14 Oct 2026). First posted on arXiv 18 Oct 2019.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 8; 2022: 14; 2023: 9; 2024: 5; 2025: 2.

38 papers.

Sort:

By area:

  1. 2022Survey of Hallucination in Natural Language Generationcited by 2,075
  2. 2023Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignmentcited by 401
  3. 2023On the Opportunities and Challenges of Foundation Models for Geospatial Artificial Intelligencecited by 88
  4. 2025A Survey of Graph Retrieval-Augmented Generation for Customized Large Language Modelscited by 88
  5. 2023Retrieving Multimodal Information for Augmented Generation: A Surveycited by 85
  6. 2022FactGraph: Evaluating Factuality in Summarization with Semantic Graph Representationscited by 41
  7. 2021Ask what's missing and what's useful: Improving Clarification Question Generation using Global Knowledgecited by 40
  8. 2021Structure-Aware Abstractive Conversation Summarization via Discourse and Action Graphscited by 36
  9. 2021Not All Memories are Created Equal: Learning to Forget by Expiringcited by 32
  10. 2021Guiding the Growth: Difficulty-Controllable Question Generation through Step-by-Step Rewritingcited by 30
  11. 2021BASS: Boosting Abstractive Summarization with Unified Semantic Graphcited by 21
  12. 2023Fourier Transformer: Fast Long Range Modeling by Removing Sequence Redundancy with FFT Operatorcited by 20
26 more
  1. 2022Knowledge Infused Decodingcited by 12
  2. 2022QASem Parsing: Text-to-text Modeling of QA-based Semanticscited by 12
  3. 2021Modeling Worlds in Textcited by 11
  4. 2022Enhanced Knowledge Selection for Grounded Dialogues via Document Semantic Graphscited by 11
  5. 2022DetIE: Multilingual Open Information Extraction Inspired by Object Detectioncited by 11
  6. 2021DocOIE: A Document-level Context-Aware Dataset for OpenIEcited by 10
  7. 2022Innovations in Neural Data-to-text Generation: A Surveycited by 10
  8. 2024Leveraging Long-Context Large Language Models for Multi-Document Understanding and Summarization in Enterprise Applicationscited by 10
  9. 2022What Makes Data-to-Text Generation Hard for Pretrained Language Models?cited by 8
  10. 2022Generating Full Length Wikipedia Biographies: The Impact of Gender Bias on the Retrieval-Based Generation of Women Biographiescited by 7
  11. 2022CompactIE: Compact Facts in Open Information Extractioncited by 5
  12. 2023Sequence-Level Certainty Reduces Hallucination In Knowledge-Grounded Dialogue Generationcited by 5
  13. 2023Shaping Political Discourse using multi-source News Summarizationcited by 5
  14. 2022Descartes: Generating Short Descriptions of Wikipedia Articlescited by 4
  15. 2023Leveraging Open Information Extraction for More Robust Domain Transfer of Event Trigger Detectioncited by 4
  16. 2023Syntactically Robust Training on Partially-Observed Data for Open Information Extractioncited by 3
  17. 2021MiRANews: Dataset and Benchmarks for Multi-Resource-Assisted News Summarizationcited by 2
  18. 2022Knowledge-aware Document Summarization: A Survey of Knowledge, Embedding Methods and Architecturescited by 2
  19. 2022Knowledge is Power: Understanding Causality Makes Legal judgment Prediction Models More Generalizable and Robustcited by 2
  20. 2024Rematch: Robust and Efficient Matching of Local Knowledge Graphs to Improve Structural and Semantic Similaritycited by 1
  21. 2022Towards Generalized Open Information Extractioncited by 0
  22. 2023Shall We Trust All Relational Tuples by Open Information Extraction? A Study on Speculation Detectioncited by 0
  23. 2024A Second Look on BASS -- Boosting Abstractive Summarization with Unified Semantic Graphs -- A Replication Studycited by 0
  24. 2024Enterprise Use Cases Combining Knowledge Graphs and Natural Language Processingcited by 0
  25. 2024Probing Omissions and Distortions in Transformer-based RDF-to-Text Modelscited by 0
  26. 2025FuDoBa: Fusing Document and Knowledge Graph-based Representations with Bayesian Optimisationcited by 0