mlsanityData to 7 Oct 2026

Interactive Machine Comprehension with Dynamic Knowledge Graphs

arXiv 2109.00077 ↗First posted 31 Aug 2021cs.CLcited by 2

Not on the map. Why?

Abstract (arXiv)

Interactive machine reading comprehension (iMRC) is machine comprehension tasks where knowledge sources are partially observable. An agent must interact with an environment sequentially to gather necessary knowledge in order to answer a question. We hypothesize that graph representations are good inductive biases, which can serve as an agent's memory mechanism in iMRC tasks. We explore four different categories of graphs that can capture text information at various levels. We describe methods that dynamically build and update these graphs during information gathering, as well as neural models to encode graph representations in RL agents. Extensive experiments on iSQuAD suggest that graph representations can result in significant performance improvements for RL agents.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 52 of its 64 references that are in the map. First posted on arXiv 31 Aug 2021.

Builds on

52 of 64 references.

References · 52

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  4. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  5. 2016Layer Normalizationcited by 5,579
  6. 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,115
  7. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,016
  8. 2013Playing Atari with Deep Reinforcement Learningcited by 3,211
  9. 2019XLNet: Generalized Autoregressive Pretraining for Language Understandingcited by 2,801
  10. 2016MS MARCO: A Human Generated MAchine Reading COmprehension Datasetcited by 1,591
  11. 2018Deep Graph Infomaxcited by 1,101
  12. 2017Rainbow: Combining Improvements in Deep Reinforcement Learningcited by 774
38 more
  1. 2019ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Taskscited by 773
  2. 2018CoQA: A Conversational Question Answering Challengecited by 674
  3. 2020TyDi QA: A Benchmark for Information-Seeking Question Answering in Typologically Diverse Languagescited by 486
  4. 2015Deep Recurrent Q-Learning for Partially Observable MDPscited by 457
  5. 2018QuAC : Question Answering in Contextcited by 379
  6. 2016NewsQA: A Machine Comprehension Datasetcited by 330
  7. 2020Agent57: Outperforming the Atari Human Benchmarkcited by 300
  8. 2016Bidirectional Attention Flow for Machine Comprehensioncited by 278
  9. 2016Using the Output Embedding to Improve Language Modelscited by 266
  10. 2015Highway Networkscited by 257
  11. 2019Probing Neural Network Comprehension of Natural Language Argumentscited by 212
  12. 2019Contrastive Learning of Structured World Modelscited by 206
  13. 2019CLUTRR: A Diagnostic Benchmark for Inductive Reasoning from Textcited by 155
  14. 2019Simple BERT Models for Relation Extraction and Semantic Role Labelingcited by 154
  15. 2020Question and Answer Test-Train Overlap in Open-Domain Question Answering Datasetscited by 137
  16. 2016Analyzing the Behavior of Visual Question Answering Modelscited by 119
  17. 2015The Goldilocks Principle: Reading Children's Books with Explicit Memory Representationscited by 108
  18. 2016A Thorough Examination of the CNN/Daily Mail Reading Comprehension Taskcited by 71
  19. 2019Dynamically Fused Graph Network for Multi-hop Reasoningcited by 63
  20. 2018Did the Model Understand the Question?cited by 60
  21. 2018What Makes Reading Comprehension Questions Easier?cited by 59
  22. 2019Select, Answer and Explain: Interpretable Multi-hop Reading Comprehension over Multiple Documentscited by 57
  23. 2018Question Answering by Reasoning Across Documents with Graph Convolutional Networkscited by 56
  24. 2018Playing Text-Adventure Games with Graph-Based Deep Reinforcement Learningcited by 53
  25. 2020IIRC: A Dataset of Incomplete Information Reading Comprehension Questionscited by 52
  26. 2020Learning Dynamic Belief Graphs to Generalize on Text-Based Gamescited by 49
  27. 2016Machine Comprehension Using Match-LSTM and Answer Pointercited by 47
  28. 2020What do Models Learn from Question Answering Datasets?cited by 45
  29. 2018Counting to Explore and Generalize in Text-based Gamescited by 36
  30. 2017Making Neural QA as Simple as Possible but not Simplercited by 33
  31. 2018Neural Models for Reasoning over Multiple Mentions using Coreferencecited by 27
  32. 2021Multi-Step Reasoning Over Unstructured Text with Beam Dense Retrievalcited by 25
  33. 2018Exploring Graph-structured Passage Representation for Multi-hop Reading Comprehension with Graph Neural Networkscited by 23
  34. 2017FusionNet: Fusing via Fully-Aware Attention with Application to Machine Comprehensioncited by 22
  35. 2015Incremental Knowledge Base Construction Using DeepDivecited by 14
  36. 2019Interactive Machine Comprehension with Information Seeking Agentscited by 13
  37. 2020SRLGRN: Semantic Role Labeling Graph Reasoning Networkcited by 12
  38. 2016Towards Information-Seeking Agentscited by 4

50 most cited of 52 All 52 (JSON)

Built on by

Cited by year

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

2 papers.

  1. 2022Asking for Knowledge: Training RL Agents to Query External Knowledge Using Languagecited by 10
  2. 2023Revisiting the Role of Similarity and Dissimilarity in Best Counter Argument Retrievalcited by 1