paper-with-me

Papers

Siamese Representation Learning for Unsupervised Relation Extraction

2023-10-01 · Guangxin Zhang, Shu Chen

Unsupervised relation extraction (URE) aims at discovering underlying relations between named entity pairs from open-domain plain text without prior information on relational distribution. Existing URE models utilizing contrastive learning, which attract positive samples and repulse negative samples to promote better separation, have got decent effect. However, fine-grained relational semantic in relationship makes spurious negative samples, damaging the inherent hierarchical structure and hindering performances. To tackle this problem, we propose Siamese Representation Learning for Unsupervised Relation Extraction -- a novel framework to simply leverage positive pairs to representation learning, possessing the capability to effectively optimize relation representation of instances and retain hierarchical information in relational feature space. Experimental results show that our model significantly advances the state-of-the-art results on two benchmark datasets and detailed analyses demonstrate the effectiveness and robustness of our proposed model on unsupervised relation extraction.

📄 PDF Abstract BibTeX arXiv:2310.00552

Code (1)

gxxxzhang/siamese-ure 공식 구현 pytorch

Tasks

Contrastive LearningRelationRelation ExtractionRepresentation Learning

Similar Papers 제목 키워드 기반

Open Relation Extraction: Relational Knowledge Transfer from Supervised Data to Unsupervised Data

2019-11-01 · IJCNLP 2019 11 · Ruidong Wu, Yuan YAO, Xu Han, Ruobing Xie 외

Open relation extraction (OpenRE) aims to extract relational facts from the open-domain corpus. To this end, it discovers relation patterns between named entities and then clusters those semantically equivalent patterns …

RelationRelation ExtractionTransfer Learning

Learning Relational Representations by Analogy using Hierarchical Siamese Networks

2019-06-01 · NAACL 2019 6 · Gaetano Rossiello, Alfio Gliozzo, Robert Farrell, Nicolas Fauceglia 외

We address relation extraction as an analogy problem by proposing a novel approach to learn representations of relations expressed by their textual mentions. In our assumption, if two pairs of entities belong to the same…

Entity EmbeddingsKnowledge Base PopulationOne-Shot LearningRelation+1

Sampling strategies in Siamese Networks for unsupervised speech representation learning

2018-04-30 · Rachid Riad, Corentin Dancette, Julien Karadayi, Neil Zeghidour 외

Recent studies have investigated siamese network architectures for learning invariant speech representations using same-different side information at the word level. Here we investigate systematically an often ignored co…

Representation LearningSpeech Representation Learning

Exploring Simple Siamese Representation Learning

2020-11-20 · CVPR 2021 1 · Xinlei Chen, Kaiming He

Siamese networks have become a common structure in various recent models for unsupervised visual representation learning. These models maximize the similarity between two augmentations of one image, subject to certain co…

Representation LearningSelf-Supervised Image Classification

Deep Unsupervised Common Representation Learning for LiDAR and Camera Data using Double Siamese Networks

2020-01-03 · Andreas Bühler, Niclas Vödisch, Mathias Bürki, Lukas Schaupp

Domain gaps of sensor modalities pose a challenge for the design of autonomous robots. Taking a step towards closing this gap, we propose two unsupervised training frameworks for finding a common representation of LiDAR …

Representation Learning