mlsanityData to 7 Oct 2026

Expanding End-to-End Question Answering on Differentiable Knowledge Graphs with Intersection

arXiv 2109.05808 ↗First posted 13 Sep 2021cs.CLcited by 12

Not on the map. Why?

Abstract (arXiv)

End-to-end question answering using a differentiable knowledge graph is a promising technique that requires only weak supervision, produces interpretable results, and is fully differentiable. Previous implementations of this technique (Cohen et al., 2020) have focused on single-entity questions using a relation following operation. In this paper, we propose a model that explicitly handles multiple-entity questions by implementing a new intersection operation, which identifies the shared elements between two sets of entities. We find that introducing intersection improves performance over a baseline model on two datasets, WebQuestionsSP (69.6% to 73.3% Hits@1) and ComplexWebQuestions (39.8% to 48.7% Hits@1), and in particular, improves performance on questions with multiple entities by over 14% on WebQuestionsSP and by 19% on ComplexWebQuestions.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 10 of its 21 references that are in the map. First posted on arXiv 13 Sep 2021.

Builds on

10 of 21 references.

References · 10

  1. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  2. 2018The Web as a Knowledge-base for Answering Complex Questionscited by 409
  3. 2016Key-Value Memory Networks for Directly Reading Documentscited by 223
  4. 2019PullNet: Open Domain Question Answering with Iterative Retrieval on Knowledge Bases and Textcited by 182
  5. 2018Open Domain Question Answering Using Early Fusion of Knowledge Bases and Textcited by 167
  6. 2018Improving Text-to-SQL Evaluation Methodologycited by 133
  7. 2021TransferNet: An Effective and Transparent Framework for Multi-hop Question Answering over Relation Graphcited by 60
  8. 2020Scalable Neural Methods for Reasoning With a Symbolic Knowledge Basecited by 32
  9. 2019Don't paraphrase, detect! Rapid and Effective Data Collection for Semantic Parsingcited by 24
  10. 2019Neural Query Language: A Knowledge Base Query Language for Tensorflowcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 5; 2024: 2; 2025: 2; 2026: 1.

12 papers.

  1. 2024GNN-RAG: Graph Neural Retrieval for Large Language Model Reasoningcited by 128
  2. 2023Knowledge-Augmented Language Model Prompting for Zero-Shot Knowledge Graph Question Answeringcited by 119
  3. 2022Mintaka: A Complex, Natural, and Multilingual Dataset for End-to-End Question Answeringcited by 71
  4. 2023ChatKBQA: A Generate-then-Retrieve Framework for Knowledge Base Question Answering with Fine-tuned Large Language Modelscited by 44
  5. 2024SPINACH: SPARQL-Based Information Navigation for Challenging Real-World Questionscited by 27
  6. 2022ReaRev: Adaptive Reasoning for Question Answering over Knowledge Graphscited by 16
  7. 2023NuTrea: Neural Tree Search for Context-guided Multi-hop KGQAcited by 7
  8. 2025KERAG: Knowledge-Enhanced Retrieval-Augmented Generation for Advanced Question Answeringcited by 5
  9. 2026S-Path-RAG: Semantic-Aware Shortest-Path Retrieval Augmented Generation for Multi-Hop Knowledge Graph Question Answeringcited by 3
  10. 2023Fine-tuned LLMs Know More, Hallucinate Less with Few-Shot Sequence-to-Sequence Semantic Parsing over Wikidatacited by 2
  11. 2023Relation-Aware Question Answering for Heterogeneous Knowledge Graphscited by 1
  12. 2025KGFR: A Foundation Retriever for Generalized Knowledge Graph Question Answeringcited by 0