Challenge: Existing unsupervised relation extraction models are either generative or discriminative . however, they are hard to train without supervision and are unstable .
Approach: They propose a skewness loss and distribution distance loss to improve the performance of discriminative based models.
Outcome: The proposed models surpass current state-of-the-art on three different datasets.

Similar Papers

Revisiting Unsupervised Relation Extraction (2020.acl-main)

Copied to clipboard

Challenge: Unsupervised relation extraction (URE) extracts relations between named entities from raw text without manually-labelled data and existing knowledge bases (KBs).
Approach: They compare unsupervised relation extraction methods to generative and discriminative approaches . they conclude that entity types provide a strong inductive bias for URE .
Outcome: The proposed method outperforms generative and discriminative approaches on two popular datasets.
Unsupervised Relation Extraction: A Variational Autoencoder Approach (2021.emnlp-main)

Copied to clipboard

Challenge: Existing methods for relation extraction use latent variables and supervised training which requires large datasets.
Approach: They propose a VAE-based unsupervised relation extraction technique that uses latent variables as an intermediate variable instead of a latent variable.
Outcome: The proposed method outperforms state-of-the-art methods on the NYT dataset and outperformed existing methods.
On the Role of Discriminative Models in Generative Relation Extraction (2026.acl-long)

Copied to clipboard

Challenge: Existing methods for relation extraction (RE) are discriminative and generative . previous studies show that discriminative models can support generative RE .
Approach: They propose a framework that leverages discriminative models to produce a top-k set of candidate relations and integrates this knowledge into generative models via in-context or prompt learning.
Outcome: The proposed framework achieves state-of-the-art on five widely used RE benchmarks.
Improving Unsupervised Relation Extraction by Augmenting Diverse Sentence Pairs (2023.emnlp-main)

Copied to clipboard

Challenge: Recent studies on relation representation learning focus on contrastive learning strategies, but these studies overlook important aspects.
Approach: They propose to use within-sentence pairs augmentation and cross-sentent pairs extraction to increase diversity of positive pairs and strengthen the discriminative power of contrastive learning.
Outcome: The proposed task increases diversity of positive pairs and strengthens discriminative power . it overcomes limitations of traditional Relation Extraction tasks, which require manual annotations .
Open Relation Extraction: Relational Knowledge Transfer from Supervised Data to Unsupervised Data (D19-1)

Copied to clipboard

Challenge: Existing methods to extract relational facts from open domain corpora are time-consuming and human-intensive.
Approach: They propose a framework to learn similarity metrics of relations from labeled data . they propose to transfer relational knowledge to identify novel relations in unlabeled data.
Outcome: Experiments on two real-world datasets show that the proposed framework improves compared with state-of-the-art methods.
Open Set Relation Extraction via Unknown-Aware Training (2023.acl-long)

Copied to clipboard

Challenge: Existing supervised relation extraction methods can still misclassify unknown relations into known relations due to the lack of supervision signals.
Approach: They propose a method that regularizes the model by dynamically synthesizing negative instances that can provide the missing supervision signals.
Outcome: The proposed method achieves SOTA unknown relation detection without compromising the classification of known relations.
More Data, More Relations, More Context and More Openness: A Review and Outlook for Relation Extraction (2020.aacl-main)

Copied to clipboard

Challenge: Existing methods for extracting relational facts from text have been successful . but with explosion of Web text, human knowledge is increasing drastically .
Approach: They propose to improve relation extraction methods to extract relational facts from text . they analyze existing methods and show promising directions towards more powerful RE .
Outcome: The proposed methods can extract relational facts from text, but they are still lacking in the current field.
A Relation-Oriented Clustering Method for Open Relation Extraction (2021.emnlp-main)

Copied to clipboard

Challenge: Existing methods for open relation extraction (OpenRE) are designed for predefined relations, which cannot deal with new emerging relations in the real world.
Approach: They propose a relation-oriented clustering model that leverages readily available labeled data to learn a relationship-oriented representation.
Outcome: The proposed model reduces error rate by 29.2% and 15.7% on two datasets compared with current SOTA methods.
Learning from Noisy Labels for Entity-Centric Information Extraction (2021.emnlp-main)

Copied to clipboard

Challenge: Recent information extraction approaches can easily overfit noisy labels and suffer from performance degradation.
Approach: They propose a co-regularization framework for entity-centric information extraction that optimizes neural models with task-specific losses and regularizes them to generate similar predictions based on agreement loss.
Outcome: The proposed framework is optimized with task-specific losses and generates similar predictions based on agreement loss.
HiURE: Hierarchical Exemplar Contrastive Learning for Unsupervised Relation Extraction (2022.naacl-main)

Copied to clipboard

Challenge: Existing methods to extract relational feature signals from natural language sentences use self-supervised clustering and classification that cause gradual drift problems.
Approach: They propose a framework that derives hierarchical signals from relational feature space using cross hierarchy attention and effectively optimizes relation representation of sentences under exemplar-wise contrastive learning.
Outcome: The proposed framework can extract the relationship between entities from natural language sentences without prior knowledge on relation scope or distribution.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations