paper-with-me

Papers

Virtual Knowledge Graph Construction for Zero-Shot Domain-Specific Document Retrieval

2022-10-01 · COLING 2022 10 · Yeon Seonwoo, Seunghyun Yoon, Franck Dernoncourt, Trung Bui, Alice Oh

Domain-specific documents cover terminologies and specialized knowledge. This has been the main challenge of domain-specific document retrieval systems. Previous approaches propose domain-adaptation and transfer learning methods to alleviate this problem. However, these approaches still follow the same document representation method in previous approaches; a document is embedded into a single vector. In this study, we propose VKGDR. VKGDR represents a given corpus into a graph of entities and their relations (known as a virtual knowledge graph) and computes the relevance between queries and documents based on the graph representation. We conduct three experiments 1) domain-specific document retrieval, 2) comparison of our virtual knowledge graph construction method with previous approaches, and 3) ablation study on each component of our virtual knowledge graph. From the results, we see that unsupervised VKGDR outperforms baselines in a zero-shot setting and even outperforms fully-supervised bi-encoder. We also verify that our virtual knowledge graph construction method results in better retrieval performance than previous approaches.

📄 PDF Abstract BibTeX

Code (1)

yeonsw/vkgdr 공식 구현 pytorch

Tasks

Domain Adaptationgraph constructionRetrievalTransfer Learning

Similar Papers 제목 키워드 기반

Prompt-based Zero-shot Relation Extraction with Semantic Knowledge Augmentation

2021-12-08 · Jiaying Gong, Hoda Eldardiry

In relation triplet extraction (RTE), recognizing unseen relations for which there are no training instances is a challenging task. Efforts have been made to recognize unseen relations based on question-answering models …

ClassificationQuestion AnsweringRelationRelation Classification+6

All About Knowledge Graphs for Actions

2020-08-28 · Pallabi Ghosh, Nirat Saini, Larry S. Davis, Abhinav Shrivastava

Current action recognition systems require large amounts of training data for recognizing an action. Recent works have explored the paradigm of zero-shot and few-shot learning to learn classifiers for unseen categories o…

Action RecognitionAllFew-Shot action recognitionFew Shot Action Recognition+5

Are Large Language Models Effective Knowledge Graph Constructors?

2025-10-13 · Ruirui Chen, Weifeng Jiang, Chengwei Qin, Bo Xiong 외 arxiv

Knowledge graphs (KGs) are widely used in knowledge-intensive applications, yet it remains unclear how effectively current large language models (LLMs) can construct document-grounded KGs in a zero-shot, schema-free sett…

Information ExtractionRelation ExtractionKnowledge Graphs

Prompt-based Zero-shot Relation Classification with Semantic Knowledge Augmentation

2022-01-16 · ACL ARR January 2022 1 · Anonymous

In relation classification, recognizing unseen (new) relations for which there are no training instances is a challenging task. We propose a prompt-based model with semantic knowledge augmentation (ZS-SKA) to recognize u…

RelationRelation ClassificationSentenceZero-shot Relation Classification

Iterative Zero-Shot LLM Prompting for Knowledge Graph Construction

2023-07-03 · Salvatore Carta, Alessandro Giuliani, Leonardo Piano, Alessandro Sebastian Podda 외

In the current digitalization era, capturing and effectively representing knowledge is crucial in most real-world scenarios. In this context, knowledge graphs represent a potent tool for retrieving and organizing a vast …

graph constructionGraph GenerationKnowledge Graphs