DiffuCOMET: Contextual Commonsense Knowledge Diffusion

• URL: http://arxiv.org/abs/2402.17011v2
• Date: Tue, 01 Oct 2024 10:38:25 GMT
• Title: DiffuCOMET: Contextual Commonsense Knowledge Diffusion
• Authors: Silin Gao, Mete Ismayilzada, Mengjie Zhao, Hiromi Wakaki, Yuki Mitsufuji, Antoine Bosselut,
• Abstract summary: In this work, we develop a series of knowledge models, DiffuCOMET, that leverage diffusion to learn to reconstruct the implicit semantic connections between narrative contexts and relevant commonsense knowledge. To evaluate DiffuCOMET, we introduce new metrics for commonsense inference that more closely measure knowledge diversity and contextual relevance. Our results on two different benchmarks, ComFact and WebNLG+, show that knowledge generated by DiffuCOMET achieves a better trade-off between commonsense diversity, contextual relevance and alignment to known gold references.
• Score: 29.23102821128395
• License:
• Abstract: Inferring contextually-relevant and diverse commonsense to understand narratives remains challenging for knowledge models. In this work, we develop a series of knowledge models, DiffuCOMET, that leverage diffusion to learn to reconstruct the implicit semantic connections between narrative contexts and relevant commonsense knowledge. Across multiple diffusion steps, our method progressively refines a representation of commonsense facts that is anchored to a narrative, producing contextually-relevant and diverse commonsense inferences for an input context. To evaluate DiffuCOMET, we introduce new metrics for commonsense inference that more closely measure knowledge diversity and contextual relevance. Our results on two different benchmarks, ComFact and WebNLG+, show that knowledge generated by DiffuCOMET achieves a better trade-off between commonsense diversity, contextual relevance and alignment to known gold references, compared to baseline knowledge models.

Related papers

• Knowledge-Enhanced Hierarchical Information Correlation Learning for Multi-Modal Rumor Detection [82.94413676131545]
  We propose a novel knowledge-enhanced hierarchical information correlation learning approach (KhiCL) for multi-modal rumor detection. KhiCL exploits cross-modal joint dictionary to transfer the heterogeneous unimodality features into the common feature space. It extracts visual and textual entities from images and text, and designs a knowledge relevance reasoning strategy.
  arXiv  Detail & Related papers  (2023-06-28T06:08:20Z)
• UNTER: A Unified Knowledge Interface for Enhancing Pre-trained Language Models [100.4659557650775]
  We propose a UNified knowledge inTERface, UNTER, to provide a unified perspective to exploit both structured knowledge and unstructured knowledge. With both forms of knowledge injected, UNTER gains continuous improvements on a series of knowledge-driven NLP tasks.
  arXiv  Detail & Related papers  (2023-05-02T17:33:28Z)
• ComFact: A Benchmark for Linking Contextual Commonsense Knowledge [31.19689856957576]
  We propose the new task of commonsense fact linking, where models are given contexts and trained to identify situationally-relevant commonsense knowledge from KGs. Our novel benchmark, ComFact, contains 293k in-context relevance annotations for commonsense across four stylistically diverse datasets.
  arXiv  Detail & Related papers  (2022-10-23T09:30:39Z)
• Mind the Gap! Injecting Commonsense Knowledge for Abstractive Dialogue Summarization [13.863545975204019]
  We present SICK, a framework that uses commonsense inferences as additional context. With injected commonsense knowledge, our framework generates more informative and consistent summaries than existing methods.
  arXiv  Detail & Related papers  (2022-09-02T10:08:28Z)
• Commonsense Knowledge in Word Associations and ConceptNet [37.751909219863585]
  This paper presents an in-depth comparison of two large-scale resources of general knowledge: ConcpetNet and SWOW. We examine the structure, overlap and differences between the two graphs, as well as the extent to which they encode situational commonsense knowledge.
  arXiv  Detail & Related papers  (2021-09-20T06:06:30Z)
• CO-NNECT: A Framework for Revealing Commonsense Knowledge Paths as Explicitations of Implicit Knowledge in Texts [12.94206336329289]
  We leverage commonsense knowledge in form of knowledge paths to establish connections between sentences. These connections can be direct (singlehop paths) or require intermediate concepts (multihop paths)
  arXiv  Detail & Related papers  (2021-05-07T10:43:43Z)
• Distilling Audio-Visual Knowledge by Compositional Contrastive Learning [51.20935362463473]
  We learn a compositional embedding that closes the cross-modal semantic gap. We establish a new, comprehensive multi-modal distillation benchmark on three video datasets.
  arXiv  Detail & Related papers  (2021-04-22T09:31:20Z)
• Improving Machine Reading Comprehension with Contextualized Commonsense Knowledge [62.46091695615262]
  We aim to extract commonsense knowledge to improve machine reading comprehension. We propose to represent relations implicitly by situating structured knowledge in a context. We employ a teacher-student paradigm to inject multiple types of contextualized knowledge into a student machine reader.
  arXiv  Detail & Related papers  (2020-09-12T17:20:01Z)
• Inferential Text Generation with Multiple Knowledge Sources and Meta-Learning [117.23425857240679]
  We study the problem of generating inferential texts of events for a variety of commonsense like textitif-else relations. Existing approaches typically use limited evidence from training examples and learn for each relation individually. In this work, we use multiple knowledge sources as fuels for the model.
  arXiv  Detail & Related papers  (2020-04-07T01:49:18Z)
• Sequential Latent Knowledge Selection for Knowledge-Grounded Dialogue [51.513276162736844]
  We propose a sequential latent variable model as the first approach to this matter. The model named sequential knowledge transformer (SKT) can keep track of the prior and posterior distribution over knowledge.
  arXiv  Detail & Related papers  (2020-02-18T11:59:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.