mlsanityData to 7 Oct 2026

Mind the Gap! Injecting Commonsense Knowledge for Abstractive Dialogue Summarization

arXiv 2209.00930 ↗First posted 2 Sep 2022cs.CL cs.AI cs.LGcited by 14

Not on the map. Why?

Abstract (arXiv)

In this paper, we propose to leverage the unique characteristics of dialogues sharing commonsense knowledge across participants, to resolve the difficulties in summarizing them. We present SICK, a framework that uses commonsense inferences as additional context. Compared to previous work that solely relies on the input dialogue, SICK uses an external knowledge model to generate a rich set of commonsense inferences and selects the most probable one with a similarity-based selection method. Built upon SICK, SICK++ utilizes commonsense as supervision, where the task of generating commonsense inferences is added upon summarizing the dialogue in a multi-task learning setting. Experimental results show that with injected commonsense knowledge, our framework generates more informative and consistent summaries than existing methods.

Key facts. Cited by 14 papers in the map (data through 7 Oct 2026). Builds on 46 of its 64 references that are in the map. First posted on arXiv 2 Sep 2022.

Builds on

46 of 64 references.

References · 46

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  4. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  5. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  6. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,462
  7. 2017A Broad-Coverage Challenge Corpus for Sentence Understanding through Inferencecited by 2,665
  8. 2020Big Bird: Transformers for Longer Sequencescited by 1,673
  9. 2018Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarizationcited by 1,308
  10. 2017Get To The Point: Summarization with Pointer-Generator Networkscited by 1,281
  11. 2019PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarizationcited by 1,100
  12. 2016ConceptNet 5.5: An Open Multilingual Graph of General Knowledgecited by 1,065
34 more
  1. 2019What Does BERT Look At? An Analysis of BERT's Attentioncited by 994
  2. 2019DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generationcited by 842
  3. 2016Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyondcited by 809
  4. 2020A Primer in BERTology: What we know about how BERT workscited by 807
  5. 2019Unified Language Model Pre-training for Natural Language Understanding and Generationcited by 668
  6. 2017DailyDialog: A Manually Labelled Multi-turn Dialogue Datasetcited by 649
  7. 2019SAMSum Corpus: A Human-annotated Dialogue Dataset for Abstractive Summarizationcited by 530
  8. 2019COMET: Commonsense Transformers for Automatic Knowledge Graph Constructioncited by 450
  9. 2015A Neural Attention Model for Abstractive Sentence Summarizationcited by 394
  10. 2021Symbolic Knowledge Distillation: from General Language Models to Commonsense Modelscited by 270
  11. 2020COMET-ATOMIC 2020: On Symbolic and Neural Commonsense Knowledge Graphscited by 254
  12. 2016SummaRuNNer: A Recurrent Neural Network based Sequence Model for Extractive Summarization of Documentscited by 245
  13. 2019Pay Less Attention with Lightweight and Dynamic Convolutionscited by 211
  14. 2020Extractive Summarization as Text Matchingcited by 189
  15. 2021DialogSum: A Real-Life Scenario Dialogue Summarization Datasetcited by 181
  16. 2018Bottom-Up Abstractive Summarizationcited by 177
  17. 2020Unsupervised Commonsense Question Answering with Self-Talkcited by 161
  18. 2021MediaSum: A Large-scale Media Interview Dataset for Dialogue Summarizationcited by 104
  19. 2018Conversational AI: The Science Behind the Alexa Prizecited by 63
  20. 2021Conversations Are Not Flat: Modeling the Dynamic Information Flow across Dialogue Utterancescited by 40
  21. 2021It's not Rocket Science : Interpreting Figurative Language in Narrativescited by 39
  22. 2021Structure-Aware Abstractive Conversation Summarization via Discourse and Action Graphscited by 36
  23. 2020RICA: Evaluating Robust Inference Capabilities Based on Commonsense Axiomscited by 28
  24. 2021Controllable Abstractive Dialogue Summarization with Sketch Supervisioncited by 27
  25. 2021Think Before You Speak: Explicitly Generating Implicit Commonsense Knowledge for Response Generationcited by 26
  26. 2021Incorporating Commonsense Knowledge Graph in Pretrained Models for Social Commonsense Taskscited by 24
  27. 2020Paragraph-level Commonsense Transformers with Recurrent Memorycited by 23
  28. 2020Incorporating Commonsense Knowledge into Abstractive Dialogue Summarization via Heterogeneous Graph Networkscited by 22
  29. 2018Neural Latent Extractive Document Summarizationcited by 20
  30. 2021Retrieval Enhanced Model for Commonsense Generationcited by 18
  31. 2019Dynamic Neuro-Symbolic Knowledge Graph Construction for Zero-shot Commonsense Question Answeringcited by 16
  32. 2021Probing Commonsense Explanation in Dialogue Response Generationcited by 13
  33. 2020Commonsense Evidence Generation and Injection in Reading Comprehensioncited by 7
  34. 2022Modularized Transfer Learning with Multiple Knowledge Graphs for Zero-shot Commonsense Reasoningcited by 5

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 9; 2024: 2; 2025: 2.

14 papers.

Sort:

By area:

  1. 2023A Systematic Study and Comprehensive Evaluation of ChatGPT on Benchmark Datasetscited by 123
  2. 2023OmniVec: Learning robust representations with cross modal sharingcited by 44
  3. 2023Dialogue Chain-of-Thought Distillation for Commonsense-aware Conversational Agentscited by 41
  4. 2025OmniVec2 -- A Novel Transformer based Network for Large Scale Multimodal and Multitask Learningcited by 13
  5. 2023CRoW: Benchmarking Commonsense Reasoning in Real-World Taskscited by 8
  6. 2023Commonsense Reasoning for Conversational AI: A Survey of the State of the Artcited by 7
  7. 2023Multi-Stage Pre-training Enhanced by ChatGPT for Multi-Scenario Multi-Domain Dialogue Summarizationcited by 7
  8. 2025An Evaluation of Large Language Models on Text Summarization Tasks Using Prompt Engineering Techniquescited by 6
  9. 2024ConvoSense: Overcoming Monotonous Commonsense Inferences for Conversational AIcited by 4
  10. 2022Taxonomy of Abstractive Dialogue Summarization: Scenarios, Approaches and Future Directionscited by 3
  11. 2024A Novel LLM-based Two-stage Summarization Approach for Long Dialoguescited by 3
  12. 2023COMET-M: Reasoning about Multiple Events in Complex Sentencescited by 2
2 more
  1. 2023Dialogue Agents 101: A Beginner's Guide to Critical Ingredients for Designing Effective Conversational Systemscited by 1
  2. 2023CASE: Commonsense-Augmented Score with an Expanded Answer Spacecited by 0