Clustering-based Unsupervised Generative Relation Extraction

• URL: http://arxiv.org/abs/2009.12681v1
• Date: Sat, 26 Sep 2020 20:36:40 GMT
• Title: Clustering-based Unsupervised Generative Relation Extraction
• Authors: Chenhan Yuan, Ryan Rossi, Andrew Katz, and Hoda Eldardiry
• Abstract summary: We propose a Clustering-based Unsupervised generative Relation Extraction framework (CURE) We use an "Encoder-Decoder" architecture to perform self-supervised learning so the encoder can extract relation information. Our model performs better than state-of-the-art models on both New York Times (NYT) and United Nations Parallel Corpus (UNPC) standard datasets.
• Score: 3.342376225738321
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This paper focuses on the problem of unsupervised relation extraction. Existing probabilistic generative model-based relation extraction methods work by extracting sentence features and using these features as inputs to train a generative model. This model is then used to cluster similar relations. However, these methods do not consider correlations between sentences with the same entity pair during training, which can negatively impact model performance. To address this issue, we propose a Clustering-based Unsupervised generative Relation Extraction (CURE) framework that leverages an "Encoder-Decoder" architecture to perform self-supervised learning so the encoder can extract relation information. Given multiple sentences with the same entity pair as inputs, self-supervised learning is deployed by predicting the shortest path between entity pairs on the dependency graph of one of the sentences. After that, we extract the relation information using the well-trained encoder. Then, entity pairs that share the same relation are clustered based on their corresponding relation information. Each cluster is labeled with a few words based on the words in the shortest paths corresponding to the entity pairs in each cluster. These cluster labels also describe the meaning of these relation clusters. We compare the triplets extracted by our proposed framework (CURE) and baseline methods with a ground-truth Knowledge Base. Experimental results show that our model performs better than state-of-the-art models on both New York Times (NYT) and United Nations Parallel Corpus (UNPC) standard datasets.

Related papers

• TacoERE: Cluster-aware Compression for Event Relation Extraction [47.89154684352463]
  Event relation extraction is a critical and fundamental challenge for natural language processing. We propose a cluster-aware compression method for improving event relation extraction (TacoERE)
  arXiv  Detail & Related papers  (2024-05-11T03:06:08Z)
• Entity or Relation Embeddings? An Analysis of Encoding Strategies for Relation Extraction [19.019881161010474]
  Relation extraction is essentially a text classification problem, which can be tackled by fine-tuning a pre-trained language model (LM) Existing approaches therefore solve the problem in an indirect way: they fine-tune an LM to learn embeddings of the head and tail entities, and then predict the relationship from these entity embeddings. Our hypothesis in this paper is that relation extraction models can be improved by capturing relationships in a more direct way.
  arXiv  Detail & Related papers  (2023-12-18T09:58:19Z)
• It Takes Two Flints to Make a Fire: Multitask Learning of Neural Relation and Explanation Classifiers [40.666590079580544]
  We propose an explainable approach for relation extraction that mitigates the tension between generalization and explainability. Our approach uses a multi-task learning architecture, which jointly trains a classifier for relation extraction. We convert the model outputs to rules to bring global explanations to this approach.
  arXiv  Detail & Related papers  (2022-04-25T03:53:12Z)
• ACTIVE:Augmentation-Free Graph Contrastive Learning for Partial Multi-View Clustering [52.491074276133325]
  We propose an augmentation-free graph contrastive learning framework to solve the problem of partial multi-view clustering. The proposed approach elevates instance-level contrastive learning and missing data inference to the cluster-level, effectively mitigating the impact of individual missing data on clustering.
  arXiv  Detail & Related papers  (2022-03-01T02:32:25Z)
• A Relation-Oriented Clustering Method for Open Relation Extraction [18.20811491136624]
  We propose a relation-oriented clustering model and use it to identify the novel relations in the unlabeled data. We minimize distance between the instance with same relation by gathering the instances towards their corresponding relation centroids. Experimental results show that our method reduces the error rate by 29.2% and 15.7%, on two datasets respectively.
  arXiv  Detail & Related papers  (2021-09-15T10:46:39Z)
• Element Intervention for Open Relation Extraction [27.408443348900057]
  OpenRE aims to cluster relation instances referring to the same underlying relation. Current OpenRE models are commonly trained on the datasets generated from distant supervision. In this paper, we revisit the procedure of OpenRE from a causal view.
  arXiv  Detail & Related papers  (2021-06-17T14:37:13Z)
• Relation Clustering in Narrative Knowledge Graphs [71.98234178455398]
  relational sentences in the original text are embedded (with SBERT) and clustered in order to merge together semantically similar relations. Preliminary tests show that such clustering might successfully detect similar relations, and provide a valuable preprocessing for semi-supervised approaches.
  arXiv  Detail & Related papers  (2020-11-27T10:43:04Z)
• Relation Extraction with Contextualized Relation Embedding (CRE) [6.030060645424665]
  This paper proposes an architecture for the relation extraction task that integrates semantic information with knowledge base modeling. We present a model architecture that internalizes KB modeling in relation extraction. The proposed CRE model achieves state of the art performance on datasets derived from The New York Times Annotated Corpus and FreeBase.
  arXiv  Detail & Related papers  (2020-11-19T05:19:46Z)
• Relation-Guided Representation Learning [53.60351496449232]
  We propose a new representation learning method that explicitly models and leverages sample relations. Our framework well preserves the relations between samples. By seeking to embed samples into subspace, we show that our method can address the large-scale and out-of-sample problem.
  arXiv  Detail & Related papers  (2020-07-11T10:57:45Z)
• LSD-C: Linearly Separable Deep Clusters [145.89790963544314]
  We present LSD-C, a novel method to identify clusters in an unlabeled dataset. Our method draws inspiration from recent semi-supervised learning practice and proposes to combine our clustering algorithm with self-supervised pretraining and strong data augmentation. We show that our approach significantly outperforms competitors on popular public image benchmarks including CIFAR 10/100, STL 10 and MNIST, as well as the document classification dataset Reuters 10K.
  arXiv  Detail & Related papers  (2020-06-17T17:58:10Z)
• SelfORE: Self-supervised Relational Feature Learning for Open Relation Extraction [60.08464995629325]
  Open-domain relation extraction is the task of extracting open-domain relation facts from natural language sentences. We proposed a self-supervised framework named SelfORE, which exploits weak, self-supervised signals. Experimental results on three datasets show the effectiveness and robustness of SelfORE.
  arXiv  Detail & Related papers  (2020-04-06T07:23:17Z)

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.