An Ontology-Guided, Deduplication-Aware Extraction Layer for Knowledge Graph Construction from Heterogeneous Documents

• URL: http://arxiv.org/abs/2607.28662v1
• Date: Wed, 22 Jul 2026 09:45:26 GMT
• Title: An Ontology-Guided, Deduplication-Aware Extraction Layer for Knowledge Graph Construction from Heterogeneous Documents
• Abstract summary: This paper presents the design, implementation, and empirical refinement of a production extraction layer that converts a live document stream into a validated knowledge graph aligned to a formal ontology.<n>The relevant slice of a curated ontology is retrieved live from a graph database by embedding similarity and injected into the extraction prompt.<n>Extracted results then pass through a refinement pipeline of five stages: deterministic cleaning, merging across chunks, a second pass for relationships, six deduplication algorithms that require no model inference, and an embedding resolution subsystem whose conflict guard no similarity score can override.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Large language models extract entities and relationships from unstructured documents fluently but inconsistently: type vocabularies fracture across documents, the same person surfaces under several name variants, relationships duplicate, and distinct individuals who share a name risk silent conflation. This paper presents the design, implementation, and empirical refinement of a production extraction layer that converts a live document stream into a validated knowledge graph aligned to a formal ontology. The system consumes document metadata from Kafka, routes PDF, spreadsheet, Office, and image content through handlers built for each format, and extracts entities and relationships in two passes using a locally hosted Qwen3.5-9B model tuned on the ontology. Its distinguishing component is ontology-guided extraction: the relevant slice of a curated ontology is retrieved live from a graph database by embedding similarity and injected into the extraction prompt, reducing catalog overhead by about 94 percent relative to static domain slices. Extracted results then pass through a refinement pipeline of five stages: deterministic cleaning, merging across chunks, a second pass for relationships, six deduplication algorithms that require no model inference, and an embedding resolution subsystem whose conflict guard no similarity score can override. Evaluation on intelligence corpora improved search recall from roughly 70 to 95 percent with no false merges, and corrected seven classes of silent quality defect, ranging from a bug that truncated source text by a single character to the systematic duplication of entities that carried title prefixes.

Related papers

• Technical Manual for a Toolkit for Measuring Contextual Individuation in Transformer Language Models [0.0]
  A transformer language model assigns a single, context-independent vector to a word type at its embedding layer, yet is widely believed to individuate that word's occurrences by context in its later layers.<n>Testing this belief cleanly requires a construct that holds the word form fixed while its context and intended sense vary in a controlled, labeled way.<n>This manual documents an open toolkit built around such a construct, which we call a bridge form.
  arXiv  Detail & Related papers  (2026-09-04T16:38:39Z)
• Curate Before You Connect: Identity and Ontology Tagging in a Production Knowledge Graph [0.0]
  This paper describes the ingestion and ontology-tagging layer that turns a validated extraction stream into a knowledge graph.<n>We describe a record-identity ladder that decides sameness from identifier columns, name columns, display names and type-scoped position rather than from name similarity.<n>We quantify the graph's conformance debt, show secondary classifications compensating for a mis-parented primary class, and describe a curation queue grown to 48,403 pending proposals against 775 human decisions.
  arXiv  Detail & Related papers  (2026-08-11T08:30:37Z)
• LEDGER: Scaling Agentic Document Editing with Dependency-aware Graph Retrieval [25.28453025760491]
  We introduce LEDGER to tackle the novel context engineering challenge of agentic document editing.<n>LEDGER constructs a lightweight dependency graph that explicitly models document structure.<n>We evaluate LEDGER on a benchmark of 1.9k test cases with various document types and lengths.
  arXiv  Detail & Related papers  (2026-06-19T17:35:05Z)
• CHOP: Chunkwise Context-Preserving Framework for RAG on Multi Documents [6.134883925217888]
  We propose CHOP, a framework that iteratively evaluates chunk relevance with Large Language Models (LLMs)<n>CHOP integrates two key components: the CNM-Extractor, which generates compact per-chunk signatures capturing categories, key nouns, and model names, and the Continuity Decision Module, which preserves contextual coherence.<n> Experiments on benchmark datasets show that CHOP alleviates retrieval confusion and provides a scalable approach for building high-quality knowledge bases.
  arXiv  Detail & Related papers  (2026-04-17T08:05:17Z)
• MoDora: Tree-Based Semi-Structured Document Analysis System [62.01015188258797]
  Semi-structured documents integrate diverse interleaved data elements arranged in various and often irregular layouts.<n>MoDora is an LLM-powered system for semi-structured document analysis.<n> Experiments show MoDora outperforms baselines by 5.97%-61.07% in accuracy.
  arXiv  Detail & Related papers  (2026-02-26T14:48:49Z)
• Learning Refined Document Representations for Dense Retrieval via Deliberate Thinking [58.69615583599489]
  Deliberate Thinking based Retriever (Debater) is a novel approach that enhances document representations by incorporating a step-by-step thinking process.<n>Debater significantly outperforms existing methods across several retrieval benchmarks.
  arXiv  Detail & Related papers  (2025-02-18T15:56:34Z)
• Graph-tree Fusion Model with Bidirectional Information Propagation for Long Document Classification [20.434941308959786]
  Long document classification presents challenges due to their extensive content and complex structure. Existing methods often struggle with token limits and fail to adequately model hierarchical relationships within documents. Our approach integrates syntax trees for sentence encodings and document graphs for document encodings, which capture fine-grained syntactic relationships and broader document contexts.
  arXiv  Detail & Related papers  (2024-10-03T19:25:01Z)
• Contextual Document Embeddings [77.22328616983417]
  We propose two complementary methods for contextualized document embeddings. First, an alternative contrastive learning objective that explicitly incorporates the document neighbors into the intra-batch contextual loss. Second, a new contextual architecture that explicitly encodes neighbor document information into the encoded representation.
  arXiv  Detail & Related papers  (2024-10-03T14:33:34Z)
• Autoregressive Search Engines: Generating Substrings as Document Identifiers [53.0729058170278]
  Autoregressive language models are emerging as the de-facto standard for generating answers. Previous work has explored ways to partition the search space into hierarchical structures. In this work we propose an alternative that doesn't force any structure in the search space: using all ngrams in a passage as its possible identifiers.
  arXiv  Detail & Related papers  (2022-04-22T10:45:01Z)
• Synthetic Document Generator for Annotation-free Layout Recognition [15.657295650492948]
  We describe a synthetic document generator that automatically produces realistic documents with labels for spatial positions, extents and categories of layout elements. We empirically illustrate that a deep layout detection model trained purely on the synthetic documents can match the performance of a model that uses real documents.
  arXiv  Detail & Related papers  (2021-11-11T01:58:44Z)
• Neural Deepfake Detection with Factual Structure of Text [78.30080218908849]
  We propose a graph-based model for deepfake detection of text. Our approach represents the factual structure of a given document as an entity graph. Our model can distinguish the difference in the factual structure between machine-generated text and human-written text.
  arXiv  Detail & Related papers  (2020-10-15T02:35:31Z)
• Fast(er) Reconstruction of Shredded Text Documents via Self-Supervised Deep Asymmetric Metric Learning [62.34197797857823]
  A central problem in automatic reconstruction of shredded documents is the pairwise compatibility evaluation of the shreds. This work proposes a scalable deep learning approach for measuring pairwise compatibility in which the number of inferences scales linearly. Our method has accuracy comparable to the state-of-the-art with a speed-up of about 22 times for a test instance with 505 shreds.
  arXiv  Detail & Related papers  (2020-03-23T03:22:06Z)
• Pairwise Multi-Class Document Classification for Semantic Relations between Wikipedia Articles [5.40541521227338]
  We model the problem of finding the relationship between two documents as a pairwise document classification task. To find semantic relation between documents, we apply a series of techniques, such as GloVe, paragraph-s, BERT, and XLNet. We perform our experiments on a newly proposed dataset of 32,168 Wikipedia article pairs and Wikidata properties that define the semantic document relations.
  arXiv  Detail & Related papers  (2020-03-22T12:52:56Z)

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.