mlsanityData to 7 Oct 2026

Relational Gating for "What If" Reasoning

arXiv 2105.13449 ↗First posted 27 May 2021cs.CLcited by 4

Not on the map. Why?

Abstract (arXiv)

This paper addresses the challenge of learning to do procedural reasoning over text to answer "What if..." questions. We propose a novel relational gating network that learns to filter the key entities and relationships and learns contextual and cross representations of both procedure and question for finding the answer. Our relational gating network contains an entity gating module, relation gating module, and contextual interaction module. These modules help in solving the "What if..." reasoning problem. We show that modeling pairwise relationships helps to capture higher-order relations and find the line of reasoning for causes and effects in the procedural descriptions. Our proposed approach achieves the state-of-the-art results on the WIQA dataset.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 20 of its 27 references that are in the map. First posted on arXiv 27 May 2021.

Builds on

20 of 27 references.

References · 20

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  4. 2017Graph Attention Networkscited by 8,854
  5. 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,115
  6. 2018Know What You Don't Know: Unanswerable Questions for SQuADcited by 1,538
  7. 2019DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphscited by 883
  8. 2016A Decomposable Attention Model for Natural Language Inferencecited by 214
  9. 2020Scalable Multi-Hop Relational Reasoning for Knowledge-Aware Question Answeringcited by 122
  10. 2020Logic-Guided Data Augmentation and Regularization for Consistent Question Answeringcited by 77
  11. 2019WIQA: A dataset for "What if..." reasoning over procedural textcited by 71
  12. 2018Tracking State Changes in Procedural Text: A Challenge Dataset and Models for Process Paragraph Comprehensioncited by 62
8 more
  1. 2016Tracking the World State with Recurrent Entity Networkscited by 51
  2. 2019Everything Happens for a Reason: Discovering the Purpose of Actions in Procedural Textcited by 31
  3. 2018Reasoning about Actions and State Changes by Injecting Commonsense Knowledgecited by 29
  4. 2020SRLGRN: Semantic Role Labeling Graph Reasoning Networkcited by 12
  5. 2020Cross-Modality Relevance for Reasoning on Language and Visioncited by 10
  6. 2020What-if I ask you to explain: Explaining the effects of perturbations in procedural textcited by 9
  7. 2020EIGEN: Event Influence GENeration using Pre-trained Language Modelscited by 8
  8. 2020REM-Net: Recursive Erasure Memory Network for Commonsense Evidence Refinementcited by 6

Built on by

Cited by year

Citing papers per year: 2022: 3; 2023: 1.

4 papers.

  1. 2023Disentangling Extraction and Reasoning in Multi-hop Spatial Reasoningcited by 6
  2. 2022Dynamic Relevance Graph Network for Knowledge-Aware Question Answeringcited by 4
  3. 2022Relevant CommonSense Subgraphs for "What if..." Procedural Reasoningcited by 2
  4. 2022elBERto: Self-supervised Commonsense Learning for Question Answeringcited by 0