Structure and Destructure: Dual Forces in the Making of Knowledge Engines

• URL: http://arxiv.org/abs/2509.00949v1
• Date: Sun, 31 Aug 2025 17:57:20 GMT
• Title: Structure and Destructure: Dual Forces in the Making of Knowledge Engines
• Authors: Yihong Chen,
• Abstract summary: The making of knowledge engines in natural language processing has been shaped by two seemingly distinct paradigms.<n>The structured paradigm leverages predefined symbolic interactions, such as knowledge graphs, as priors and designs models to capture them.<n>The unstructured paradigm centers on scaling transformer architectures with increasingly vast data and model sizes, as seen in modern large language models.
• Score: 9.115474230901873
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: The making of knowledge engines in natural language processing has been shaped by two seemingly distinct paradigms: one grounded in structure, the other driven by massively available unstructured data. The structured paradigm leverages predefined symbolic interactions, such as knowledge graphs, as priors and designs models to capture them. In contrast, the unstructured paradigm centers on scaling transformer architectures with increasingly vast data and model sizes, as seen in modern large language models. Despite their divergence, this thesis seeks to establish conceptual connections bridging these paradigms. Two complementary forces, structure and destructure, emerge across both paradigms: structure organizes seen symbolic interactions, while destructure, through periodic embedding resets, improves model plasticity and generalization to unseen scenarios. These connections form a new recipe for developing general knowledge engines that can support transparent, controllable, and adaptable intelligent systems.

Related papers

• Cross-Model Semantics in Representation Learning [1.2064681974642195]
  We show that structural regularities induce representational geometry that is more stable under architectural variation.<n>This suggests that certain forms of inductive bias not only support generalization within a model, but also improve the interoperability of learned features across models.
  arXiv  Detail & Related papers  (2025-08-05T16:57:24Z)
• Information Structure in Mappings: An Approach to Learning, Representation, and Generalisation [3.8073142980733]
  This thesis introduces quantitative methods for identifying systematic structure in a mapping between spaces.<n>I identify structural primitives present in a mapping, along with information theoretics of each.<n>I also introduce a novel, performant, approach to estimating the entropy of vector space, that allows this analysis to be applied to models ranging in size from 1 million to 12 billion parameters.
  arXiv  Detail & Related papers  (2025-05-29T19:27:50Z)
• Directional Non-Commutative Monoidal Structures for Compositional Embeddings in Machine Learning [0.0]
  We introduce a new structure for compositional embeddings built on directional non-commutative monoidal operators.<n>Our construction defines a distinct composition operator circ_i for each axis i, ensuring associative combination along each axis without imposing global commutativity.<n>All axis-specific operators commute with one another, enforcing a global interchange law that enables consistent crossaxis compositions.
  arXiv  Detail & Related papers  (2025-05-21T13:27:14Z)
• Scaling Laws and Representation Learning in Simple Hierarchical Languages: Transformers vs. Convolutional Architectures [49.19753720526998]
  We derive theoretical scaling laws for neural network performance on synthetic datasets.<n>We validate that convolutional networks, whose structure aligns with that of the generative process through locality and weight sharing, enjoy a faster scaling of performance.<n>This finding clarifies the architectural biases underlying neural scaling laws and highlights how representation learning is shaped by the interaction between model architecture and the statistical properties of data.
  arXiv  Detail & Related papers  (2025-05-11T17:44:14Z)
• MGSA: Multi-Granularity Graph Structure Attention for Knowledge Graph-to-Text Generation [10.607080796475815]
  This paper introduces the Multi-granularity Graph Structure Attention (MGSA), which is based on pre-trained language models (PLMs) The encoder of the model architecture features an entity-level structure encoding module, a word-level structure encoding module, and an aggregation module that synthesizes information from both structure. We conducted extensive evaluations of the MGSA model using two widely recognized KG-to-Text Generation benchmark datasets, WebNLG and EventNarrative.
  arXiv  Detail & Related papers  (2024-09-16T14:01:03Z)
• Learning Correlation Structures for Vision Transformers [93.22434535223587]
  We introduce a new attention mechanism, dubbed structural self-attention (StructSA) We generate attention maps by recognizing space-time structures of key-query correlations via convolution. This effectively leverages rich structural patterns in images and videos such as scene layouts, object motion, and inter-object relations.
  arXiv  Detail & Related papers  (2024-04-05T07:13:28Z)
• StructRe: Rewriting for Structured Shape Modeling [60.20359722058389]
  We present StructRe, a structure rewriting system, as a novel approach to structured shape modeling.<n>Given a 3D object represented by points and components, StructRe can rewrite it upward into more concise structures, or downward into more detailed structures.
  arXiv  Detail & Related papers  (2023-11-29T10:35:00Z)
• SIM-Trans: Structure Information Modeling Transformer for Fine-grained Visual Categorization [59.732036564862796]
  We propose the Structure Information Modeling Transformer (SIM-Trans) to incorporate object structure information into transformer for enhancing discriminative representation learning. The proposed two modules are light-weighted and can be plugged into any transformer network and trained end-to-end easily. Experiments and analyses demonstrate that the proposed SIM-Trans achieves state-of-the-art performance on fine-grained visual categorization benchmarks.
  arXiv  Detail & Related papers  (2022-08-31T03:00:07Z)
• Structural Biases for Improving Transformers on Translation into Morphologically Rich Languages [120.74406230847904]
  TP-Transformer augments the traditional Transformer architecture to include an additional component to represent structure. The second method imbues structure at the data level by segmenting the data with morphological tokenization. We find that each of these two approaches allows the network to achieve better performance, but this improvement is dependent on the size of the dataset.
  arXiv  Detail & Related papers  (2022-08-11T22:42:24Z)
• Integrating Knowledge Graph embedding and pretrained Language Models in Hypercomplex Spaces [29.71047521165222]
  We build on existing strong representations of single modalities and use hypercomplex algebra to represent both, (i), single-modality embedding as well as, (ii) the interaction between different modalities. More specifically, we suggest Dihedron and Quaternion representations of 4D hypercomplex numbers to integrate four modalities namely structural knowledge graph embedding, word-level representations and document-level representations. Our unified vector representation scores the plausibility of labelled edges via Hamilton and Dihedron products, thus modeling pairwise interactions between different modalities.
  arXiv  Detail & Related papers  (2022-08-04T16:18:16Z)
• S2RMs: Spatially Structured Recurrent Modules [105.0377129434636]
  We take a step towards exploiting dynamic structure that are capable of simultaneously exploiting both modular andtemporal structures. We find our models to be robust to the number of available views and better capable of generalization to novel tasks without additional training.
  arXiv  Detail & Related papers  (2020-07-13T17:44:30Z)

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.