mlsanityData to 14 Oct 2026

Self-supervised Knowledge Triplet Learning for Zero-shot Question Answering

arXiv 2005.00316 ↗First posted 1 May 2020cs.CL cs.AI cs.LGcited by 29

Not on the map. Why?

Abstract (arXiv)

The aim of all Question Answering (QA) systems is to be able to generalize to unseen questions. Current supervised methods are reliant on expensive data annotation. Moreover, such annotations can introduce unintended annotator bias which makes systems focus more on the bias than the actual task. In this work, we propose Knowledge Triplet Learning (KTL), a self-supervised task over knowledge graphs. We propose heuristics to create synthetic graphs for commonsense and scientific knowledge. We propose methods of how to use KTL to perform zero-shot QA and our experiments show considerable improvements over large pre-trained transformer models.

Key facts. Cited by 29 papers in the map (data through 14 Oct 2026). First posted on arXiv 1 May 2020.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 15; 2022: 9; 2023: 4; 2024: 1.

29 papers.

Sort:

By area:

  1. 2022State-of-the-art generalisation research in NLP: A taxonomy and reviewcited by 98
  2. 2021Prompting Contrastive Explanations for Commonsense Reasoning Taskscited by 45
  3. 2021Knowledge-aware Zero-Shot Learning: Survey and Perspectivecited by 41
  4. 2021Dimensions of Commonsense Knowledgecited by 29
  5. 2021Zero-shot and Few-shot Learning with Knowledge Graphs: A Comprehensive Surveycited by 23
  6. 2023The Life Cycle of Knowledge in Big Language Models: A Surveycited by 23
  7. 2021Self-Supervised Test-Time Learning for Reading Comprehensioncited by 22
  8. 2022Z-LaVI: Zero-Shot Language Solver Fueled by Visual Imaginationcited by 18
  9. 2022Acquiring and Modelling Abstract Commonsense Knowledge via Conceptualizationcited by 17
  10. 2021Thinking Aloud: Dynamic Context Generation Improves Zero-Shot Reasoning Performance of GPT-2cited by 15
  11. 2023Abductive Commonsense Reasoning Exploiting Mutually Exclusive Explanationscited by 11
  12. 2021A Semantic-based Method for Unsupervised Commonsense Question Answeringcited by 10
17 more
  1. 2021What Can Knowledge Bring to Machine Learning? -- A Survey of Low-shot Learning for Structured Datacited by 10
  2. 2022Distilling Hypernymy Relations from Language Models: On the Effectiveness of Zero-Shot Taxonomy Inductioncited by 8
  3. 2021DeepA2: A Modular Framework for Deep Argument Analysis with Pretrained Neural Text2Text Language Modelscited by 7
  4. 2021Unsupervised Natural Language Inference Using PHL Triplet Generationcited by 6
  5. 2022MICO: A Multi-alternative Contrastive Learning Framework for Commonsense Knowledge Representationcited by 6
  6. 2023Multi-hop Commonsense Knowledge Injection Framework for Zero-Shot Commonsense Question Answeringcited by 6
  7. 2022Automatic Detection of Entity-Manipulated Text using Factual Knowledgecited by 5
  8. 2022Modularized Transfer Learning with Multiple Knowledge Graphs for Zero-shot Commonsense Reasoningcited by 5
  9. 2022An Empirical Investigation of Commonsense Self-Supervision with Knowledge Graphscited by 4
  10. 2021Encoding Explanatory Knowledge for Zero-shot Science Question Answeringcited by 3
  11. 2021Bridging the Gap between Language Model and Reading Comprehension: Unsupervised MRC via Self-Supervisioncited by 3
  12. 2022Generalizable Neuro-symbolic Systems for Commonsense Question Answeringcited by 3
  13. 2023BUCA: A Binary Classification Approach to Unsupervised Commonsense Question Answeringcited by 3
  14. 2021Unsupervised Pronoun Resolution via Masked Noun-Phrase Predictioncited by 2
  15. 2021Transfer Learning for Multi-lingual Tasks -- a Surveycited by 1
  16. 2021ActKnow: Active External Knowledge Infusion Learning for Question Answering in Low Data Regimecited by 0
  17. 2024Unsupervised multiple choices question answering via universal corpuscited by 0