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

arXiv: https://arxiv.org/abs/1910.08435 · HTML: https://mlsanity.com/paper/1910.08435/

## Key facts

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

## Built on by (most cited first, 30 of 38)

- [Survey of Hallucination in Natural Language Generation](https://mlsanity.com/paper/2202.03629/) (2022)
- [Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment](https://mlsanity.com/paper/2308.05374/) (2023)
- [On the Opportunities and Challenges of Foundation Models for Geospatial Artificial Intelligence](https://mlsanity.com/paper/2304.06798/) (2023)
- [A Survey of Graph Retrieval-Augmented Generation for Customized Large Language Models](https://mlsanity.com/paper/2501.13958/) (2025)
- [Retrieving Multimodal Information for Augmented Generation: A Survey](https://mlsanity.com/paper/2303.10868/) (2023)
- [FactGraph: Evaluating Factuality in Summarization with Semantic Graph Representations](https://mlsanity.com/paper/2204.06508/) (2022)
- [Ask what's missing and what's useful: Improving Clarification Question Generation using Global Knowledge](https://mlsanity.com/paper/2104.06828/) (2021)
- [Structure-Aware Abstractive Conversation Summarization via Discourse and Action Graphs](https://mlsanity.com/paper/2104.08400/) (2021)
- [Not All Memories are Created Equal: Learning to Forget by Expiring](https://mlsanity.com/paper/2105.06548/) (2021)
- [Guiding the Growth: Difficulty-Controllable Question Generation through Step-by-Step Rewriting](https://mlsanity.com/paper/2105.11698/) (2021)
- [BASS: Boosting Abstractive Summarization with Unified Semantic Graph](https://mlsanity.com/paper/2105.12041/) (2021)
- [Fourier Transformer: Fast Long Range Modeling by Removing Sequence Redundancy with FFT Operator](https://mlsanity.com/paper/2305.15099/) (2023)
- [Knowledge Infused Decoding](https://mlsanity.com/paper/2204.03084/) (2022)
- [QASem Parsing: Text-to-text Modeling of QA-based Semantics](https://mlsanity.com/paper/2205.11413/) (2022)
- [Modeling Worlds in Text](https://mlsanity.com/paper/2106.09578/) (2021)
- [Enhanced Knowledge Selection for Grounded Dialogues via Document Semantic Graphs](https://mlsanity.com/paper/2206.07296/) (2022)
- [DetIE: Multilingual Open Information Extraction Inspired by Object Detection](https://mlsanity.com/paper/2206.12514/) (2022)
- [DocOIE: A Document-level Context-Aware Dataset for OpenIE](https://mlsanity.com/paper/2105.04271/) (2021)
- [Innovations in Neural Data-to-text Generation: A Survey](https://mlsanity.com/paper/2207.12571/) (2022)
- [Leveraging Long-Context Large Language Models for Multi-Document Understanding and Summarization in Enterprise Applications](https://mlsanity.com/paper/2409.18454/) (2024)
- [What Makes Data-to-Text Generation Hard for Pretrained Language Models?](https://mlsanity.com/paper/2205.11505/) (2022)
- [Generating Full Length Wikipedia Biographies: The Impact of Gender Bias on the Retrieval-Based Generation of Women Biographies](https://mlsanity.com/paper/2204.05879/) (2022)
- [CompactIE: Compact Facts in Open Information Extraction](https://mlsanity.com/paper/2205.02880/) (2022)
- [Sequence-Level Certainty Reduces Hallucination In Knowledge-Grounded Dialogue Generation](https://mlsanity.com/paper/2310.18794/) (2023)
- [Shaping Political Discourse using multi-source News Summarization](https://mlsanity.com/paper/2312.11703/) (2023)
- [Descartes: Generating Short Descriptions of Wikipedia Articles](https://mlsanity.com/paper/2205.10012/) (2022)
- [Leveraging Open Information Extraction for More Robust Domain Transfer of Event Trigger Detection](https://mlsanity.com/paper/2305.14163/) (2023)
- [Syntactically Robust Training on Partially-Observed Data for Open Information Extraction](https://mlsanity.com/paper/2301.06841/) (2023)
- [MiRANews: Dataset and Benchmarks for Multi-Resource-Assisted News Summarization](https://mlsanity.com/paper/2109.10650/) (2021)
- [Knowledge-aware Document Summarization: A Survey of Knowledge, Embedding Methods and Architectures](https://mlsanity.com/paper/2204.11190/) (2022)

## 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.