Inferring Scientific Cross-Document Coreference and Hierarchy with Definition-Augmented Relational Reasoning

• URL: http://arxiv.org/abs/2409.15113v2
• Date: Tue, 24 Sep 2024 08:18:34 GMT
• Title: Inferring Scientific Cross-Document Coreference and Hierarchy with Definition-Augmented Relational Reasoning
• Authors: Lior Forer, Tom Hope,
• Abstract summary: We present a novel method which generates context-dependent definitions of concept mentions by retrieving full-text literature. We further generate relational definitions, which describe how two concept mentions are related or different, and design an efficient re-ranking approach to address the explosion involved in inferring links across papers.
• Score: 7.086262532457526
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We address the fundamental task of inferring cross-document coreference and hierarchy in scientific texts, which has important applications in knowledge graph construction, search, recommendation and discovery. LLMs can struggle when faced with many long-tail technical concepts with nuanced variations. We present a novel method which generates context-dependent definitions of concept mentions by retrieving full-text literature, and uses the definitions to enhance detection of cross-document relations. We further generate relational definitions, which describe how two concept mentions are related or different, and design an efficient re-ranking approach to address the combinatorial explosion involved in inferring links across papers. In both fine-tuning and in-context learning settings we achieve large gains in performance. We provide analysis of generated definitions, shedding light on the relational reasoning ability of LLMs over fine-grained scientific concepts.

Related papers

• GIVE: Structured Reasoning with Knowledge Graph Inspired Veracity Extrapolation [108.2008975785364]
  Graph Inspired Veracity Extrapolation (GIVE) is a novel reasoning framework that integrates the parametric and non-parametric memories. Our method facilitates a more logical and step-wise reasoning approach akin to experts' problem-solving, rather than gold answer retrieval.
  arXiv  Detail & Related papers  (2024-10-11T03:05:06Z)
• Enriching Ontologies with Disjointness Axioms using Large Language Models [5.355177558868206]
  Large Models (LLMs) offer consistency by identifying and asserting class disjointness axioms. Our approach aims at leveraging the implicit knowledge embedded in LLMs to elicit knowledge for classifying ontological disjointness. Our findings suggest that LLMs, when guided by effective prompt strategies, can reliably identify disjointness relationships.
  arXiv  Detail & Related papers  (2024-10-04T09:00:06Z)
• URL: Universal Referential Knowledge Linking via Task-instructed Representation Compression [46.43057075676104]
  We propose universal referential knowledge linking (URL), which aims to resolve diversified referential knowledge linking tasks by one unified model. We also construct a new benchmark to evaluate ability of models on referential knowledge linking tasks across different scenarios.
  arXiv  Detail & Related papers  (2024-04-24T23:37:15Z)
• Finding Pragmatic Differences Between Disciplines [14.587150614245123]
  We learn a fixed set of domain-agnostic descriptors for document sections and "retrofit" the corpus to these descriptors. We analyze the position and ordering of these descriptors across documents to understand the relationship between discipline and structure. Our findings lay the foundation for future work in assessing research quality, domain style transfer, and further pragmatic analysis.
  arXiv  Detail & Related papers  (2023-09-30T00:46:14Z)
• 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)
• Multimodal Relation Extraction with Cross-Modal Retrieval and Synthesis [89.04041100520881]
  This research proposes to retrieve textual and visual evidence based on the object, sentence, and whole image. We develop a novel approach to synthesize the object-level, image-level, and sentence-level information for better reasoning between the same and different modalities.
  arXiv  Detail & Related papers  (2023-05-25T15:26:13Z)
• Multi-Relational Hyperbolic Word Embeddings from Natural Language Definitions [5.763375492057694]
  This paper presents a multi-relational model that explicitly leverages such a structure to derive word embeddings from definitions. An empirical analysis demonstrates that the framework can help imposing the desired structural constraints. Experiments reveal the superiority of the Hyperbolic word embeddings over the Euclidean counterparts.
  arXiv  Detail & Related papers  (2023-05-12T08:16:06Z)
• SciCo: Hierarchical Cross-Document Coreference for Scientific Concepts [28.96683772139377]
  We present a new task of hierarchical CDCR for concepts in scientific papers. The goal is to jointly inferring coreference clusters and hierarchy between them. We create SciCo, an expert-annotated dataset for this task, which is 3X larger than the prominent ECB+ resource.
  arXiv  Detail & Related papers  (2021-04-18T10:42:20Z)
• ERICA: Improving Entity and Relation Understanding for Pre-trained Language Models via Contrastive Learning [97.10875695679499]
  We propose a novel contrastive learning framework named ERICA in pre-training phase to obtain a deeper understanding of the entities and their relations in text. Experimental results demonstrate that our proposed ERICA framework achieves consistent improvements on several document-level language understanding tasks.
  arXiv  Detail & Related papers  (2020-12-30T03:35:22Z)
• Concept Learners for Few-Shot Learning [76.08585517480807]
  We propose COMET, a meta-learning method that improves generalization ability by learning to learn along human-interpretable concept dimensions. We evaluate our model on few-shot tasks from diverse domains, including fine-grained image classification, document categorization and cell type annotation.
  arXiv  Detail & Related papers  (2020-07-14T22:04:17Z)
• Explaining Relationships Between Scientific Documents [55.23390424044378]
  We address the task of explaining relationships between two scientific documents using natural language text. In this paper we establish a dataset of 622K examples from 154K documents.
  arXiv  Detail & Related papers  (2020-02-02T03:54:47Z)

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.