mlsanityData to 14 Oct 2026

Reasoning Over Virtual Knowledge Bases With Open Predicate Relations

arXiv 2102.07043 ↗First posted 14 Feb 2021cs.AI cs.CL cs.LGcited by 18

Not on the map. Why?

Abstract (arXiv)

We present the Open Predicate Query Language (OPQL); a method for constructing a virtual KB (VKB) trained entirely from text. Large Knowledge Bases (KBs) are indispensable for a wide-range of industry applications such as question answering and recommendation. Typically, KBs encode world knowledge in a structured, readily accessible form derived from laborious human annotation efforts. Unfortunately, while they are extremely high precision, KBs are inevitably highly incomplete and automated methods for enriching them are far too inaccurate. Instead, OPQL constructs a VKB by encoding and indexing a set of relation mentions in a way that naturally enables reasoning and can be trained without any structured supervision. We demonstrate that OPQL outperforms prior VKB methods on two different KB reasoning tasks and, additionally, can be used as an external memory integrated into a language model (OPQL-LM) leading to improvements on two open-domain question answering tasks.

Key facts. Cited by 18 papers in the map (data through 14 Oct 2026). Builds on 28 of its 40 references that are in the map. First posted on arXiv 14 Feb 2021.

Builds on

28 of 40 references.

References · 28

  1. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  3. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,893
  4. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  5. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,141
  6. 2017Reading Wikipedia to Answer Open-Domain Questionscited by 777
  7. 2019Latent Retrieval for Weakly Supervised Open Domain Question Answeringcited by 695
  8. 2018The Web as a Knowledge-base for Answering Complex Questionscited by 410
  9. 2019Knowledge Enhanced Contextual Word Representationscited by 296
  10. 2019Matching the Blanks: Distributional Similarity for Relation Learningcited by 272
  11. 2016Key-Value Memory Networks for Directly Reading Documentscited by 223
  12. 2019PullNet: Open Domain Question Answering with Iterative Retrieval on Knowledge Bases and Textcited by 184
16 more
  1. 2017Variational Reasoning for Question Answering with Knowledge Graphcited by 170
  2. 2018Open Domain Question Answering Using Early Fusion of Knowledge Bases and Textcited by 168
  3. 2016Neural Symbolic Machines: Learning Semantic Parsers on Freebase with Weak Supervisioncited by 103
  4. 2020Entities as Experts: Sparse Memory Access with Entity Supervisioncited by 100
  5. 2019Barack's Wife Hillary: Using Knowledge-Graphs for Fact-Aware Language Modelingcited by 71
  6. 2019Real-Time Open-Domain Question Answering with Dense-Sparse Phrase Indexcited by 64
  7. 2016Tracking the World State with Recurrent Entity Networkscited by 51
  8. 2018Knowledgeable Reader: Enhancing Cloze-Style Reading Comprehension with External Commonsense Knowledgecited by 48
  9. 2017Neural Natural Language Inference Models Enhanced with External Knowledgecited by 40
  10. 2020Differentiable Reasoning over a Virtual Knowledge Basecited by 39
  11. 2020Facts as Experts: Adaptable and Interpretable Neural Memory over Symbolic Knowledgecited by 37
  12. 2020Scalable Neural Methods for Reasoning With a Symbolic Knowledge Basecited by 32
  13. 2018Phrase-Indexed Question Answering: A New Challenge for Scalable Document Comprehensioncited by 23
  14. 2016A Neural Knowledge Language Modelcited by 13
  15. 2020Learning Cross-Context Entity Representations from Textcited by 12
  16. 2017Dynamic Integration of Background Knowledge in Neural NLU Systemscited by 7

Built on by

Cited by year

Citing papers per year: 2021: 5; 2022: 7; 2023: 4; 2024: 2.

18 papers.

Sort:

By area:

  1. 2021Pre-Trained Models: Past, Present and Futurecited by 319
  2. 2022A Review on Language Models as Knowledge Basescited by 157
  3. 2021Complex Knowledge Base Question Answering: A Surveycited by 52
  4. 2021Mention Memory: incorporating textual knowledge into Transformers through entity mention attentioncited by 43
  5. 2022QAMPARI: An Open-domain Question Answering Benchmark for Questions with Many Answers from Multiple Paragraphscited by 42
  6. 2022Faithful to the Document or to the World? Mitigating Hallucinations via Entity-linked Knowledge in Abstractive Summarizationcited by 20
  7. 2022Augmenting Pre-trained Language Models with QA-Memory for Open-Domain Question Answeringcited by 19
  8. 2021Iterative Hierarchical Attention for Answering Complex Questions over Long Documentscited by 10
  9. 2022Zemi: Learning Zero-Shot Semi-Parametric Language Models from Multiple Taskscited by 8
  10. 2021Relation-Guided Pre-Training for Open-Domain Question Answeringcited by 7
  11. 2022A Unified Encoder-Decoder Framework with Entity Memorycited by 7
  12. 2022QA Is the New KR: Question-Answer Pairs as Knowledge Basescited by 6
6 more
  1. 2023Single Sequence Prediction over Reasoning Graphs for Multi-hop QAcited by 5
  2. 2024Automating IRAC Analysis in Malaysian Contract Law using a Semi-Structured Knowledge Basecited by 5
  3. 2023Answering Ambiguous Questions with a Database of Questions, Answers, and Revisionscited by 4
  4. 2023Towards Corpus-Scale Discovery of Selection Biases in News Coverage: Comparing What Sources Say About Entities as a Startcited by 1
  5. 2023Semi-supervised Relation Extraction via Data Augmentation and Consistency-trainingcited by 1
  6. 2024READ: Improving Relation Extraction from an ADversarial Perspectivecited by 0