A Novel Global Feature-Oriented Relational Triple Extraction Model based on Table Filling

• URL: http://arxiv.org/abs/2109.06705v1
• Date: Tue, 14 Sep 2021 14:13:42 GMT
• Title: A Novel Global Feature-Oriented Relational Triple Extraction Model based on Table Filling
• Authors: Feiliang Ren, Longhui Zhang, Shujuan Yin, Xiaofeng Zhao, Shilei Liu, Bochao Li, Yaduo Liu
• Abstract summary: We propose a global feature-oriented triple extraction model that makes full use of the mentioned two kinds of global associations. Experimental results show our model is effective and it achieves state-of-the-art results on all of these datasets.
• Score: 1.6295073821494463
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Table filling based relational triple extraction methods are attracting growing research interests due to their promising performance and their abilities on extracting triples from complex sentences. However, this kind of methods are far from their full potential because most of them only focus on using local features but ignore the global associations of relations and of token pairs, which increases the possibility of overlooking some important information during triple extraction. To overcome this deficiency, we propose a global feature-oriented triple extraction model that makes full use of the mentioned two kinds of global associations. Specifically, we first generate a table feature for each relation. Then two kinds of global associations are mined from the generated table features. Next, the mined global associations are integrated into the table feature of each relation. This "generate-mine-integrate" process is performed multiple times so that the table feature of each relation is refined step by step. Finally, each relation's table is filled based on its refined table feature, and all triples linked to this relation are extracted based on its filled table. We evaluate the proposed model on three benchmark datasets. Experimental results show our model is effective and it achieves state-of-the-art results on all of these datasets. The source code of our work is available at: https://github.com/neukg/GRTE.

Related papers

• RTF: Region-based Table Filling Method for Relational Triple Extraction [17.267920424291372]
  We propose a novel Region-based Table Filling method (RT) for extracting triples from knowledge graphs. We devise a novel regionbased tagging scheme and bi-directional decoding strategy, which regard each triple as a region on the relation-specific table, and identifies triples by determining two endpoints of each region. Experimental results show our method achieves better generalization capability on three variants of two widely used benchmark datasets.
  arXiv  Detail & Related papers  (2024-04-29T23:36:38Z)
• A Bi-consolidating Model for Joint Relational Triple Extraction [3.972061685570092]
  Current methods to extract relational triples directly make a prediction based on a possible entity pair in a raw sentence without depending on entity recognition. The task suffers from a serious semantic overlapping problem, in which several relation triples may share one or two entities in a sentence. A bi-consolidating model is proposed to address this problem by simultaneously reinforcing the local and global semantic features relevant to a relation triple.
  arXiv  Detail & Related papers  (2024-04-05T04:04:23Z)
• Prompt Based Tri-Channel Graph Convolution Neural Network for Aspect Sentiment Triplet Extraction [63.0205418944714]
  Aspect Sentiment Triplet Extraction (ASTE) is an emerging task to extract a given sentence's triplets, which consist of aspects, opinions, and sentiments. Recent studies tend to address this task with a table-filling paradigm, wherein word relations are encoded in a two-dimensional table. We propose a novel model for the ASTE task, called Prompt-based Tri-Channel Graph Convolution Neural Network (PT-GCN), which converts the relation table into a graph to explore more comprehensive relational information.
  arXiv  Detail & Related papers  (2023-12-18T12:46:09Z)
• Relational Deep Learning: Graph Representation Learning on Relational Databases [69.7008152388055]
  We introduce an end-to-end representation approach to learn on data laid out across multiple tables. Message Passing Graph Neural Networks can then automatically learn across the graph to extract representations that leverage all data input.
  arXiv  Detail & Related papers  (2023-12-07T18:51:41Z)
• A Dataset for Hyper-Relational Extraction and a Cube-Filling Approach [59.89749342550104]
  We propose the task of hyper-relational extraction to extract more specific and complete facts from text. Existing models cannot perform hyper-relational extraction as it requires a model to consider the interaction between three entities. We propose CubeRE, a cube-filling model inspired by table-filling approaches and explicitly considers the interaction between relation triplets and qualifiers.
  arXiv  Detail & Related papers  (2022-11-18T03:51:28Z)
• UniRel: Unified Representation and Interaction for Joint Relational Triple Extraction [29.15806644012706]
  We propose UniRel to address the challenges of capturing rich correlations between entities and relations. Specifically, we unify representations of entities and relations by jointly encoding them within a relationald natural language sequence. With comprehensive experiments on two popular triple extraction datasets, we demonstrate that UniRel is more effective computationally efficient.
  arXiv  Detail & Related papers  (2022-11-16T16:53:13Z)
• RelationPrompt: Leveraging Prompts to Generate Synthetic Data for Zero-Shot Relation Triplet Extraction [65.4337085607711]
  We introduce the task setting of Zero-Shot Relation Triplet Extraction (ZeroRTE) Given an input sentence, each extracted triplet consists of the head entity, relation label, and tail entity where the relation label is not seen at the training stage. We propose to synthesize relation examples by prompting language models to generate structured texts.
  arXiv  Detail & Related papers  (2022-03-17T05:55:14Z)
• A Hierarchical Entity Graph Convolutional Network for Relation Extraction across Documents [29.183245395412705]
  We propose cross-document relation extraction, where the two entities of a relation appear in two different documents. Following this idea, we create a dataset for two-hop relation extraction, where each chain contains exactly two documents. Our proposed dataset covers a higher number of relations than the publicly available sentence-level datasets.
  arXiv  Detail & Related papers  (2021-08-21T12:33:50Z)
• PRGC: Potential Relation and Global Correspondence Based Joint Relational Triple Extraction [23.998135821388203]
  We propose a joint relational triple extraction framework based on Potential Relation and Global Correspondence (PRGC) PRGC achieves state-of-the-art performance on public benchmarks with higher efficiency and delivers consistent performance gain on complex scenarios of overlapping triples.
  arXiv  Detail & Related papers  (2021-06-18T03:38:07Z)
• TCN: Table Convolutional Network for Web Table Interpretation [52.32515851633981]
  We propose a novel table representation learning approach considering both the intra- and inter-table contextual information. Our method can outperform competitive baselines by +4.8% of F1 for column type prediction and by +4.1% of F1 for column pairwise relation prediction.
  arXiv  Detail & Related papers  (2021-02-17T02:18:10Z)
• HittER: Hierarchical Transformers for Knowledge Graph Embeddings [85.93509934018499]
  We propose Hitt to learn representations of entities and relations in a complex knowledge graph. Experimental results show that Hitt achieves new state-of-the-art results on multiple link prediction. We additionally propose a simple approach to integrate Hitt into BERT and demonstrate its effectiveness on two Freebase factoid answering datasets.
  arXiv  Detail & Related papers  (2020-08-28T18:58:15Z)

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.