RECORD
Jointly Extracting Relations with Class Ties via Effective Deep Ranking
Artificial Intelligence · Submitted 22 Dec 2016
abstract compiled · 2026-09-23 · no language-model review
The authors' main claim Our model outperforms the baselines significantly, achieving state-of-the-art performance.
The compiled record
The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.
Open the compiled record
The abstract, sentence by sentence
Connections between relations in relation extraction, which we call class ties, are common. In distantly supervised scenario, one entity tuple may have multiple relation facts. Exploiting class ties between relations of one entity tuple will be promising for distantly supervised relation extraction. However, previous models are not effective or ignore to model this property. In this work, to effectively leverage class ties, we propose to make joint relation extraction with a unified model that integrates convolutional neural network (CNN) with a general pairwise ranking framework, in which three novel ranking loss functions are introduced. Additionally, an effective method is presented to relieve the severe class imbalance problem from NR (not relation) for model training. Experiments on a widely used dataset show that leveraging class ties will enhance extraction and demonstrate the effectiveness of our model to learn class ties. Our model outperforms the baselines significantly, achieving state-of-the-art performance.
background contribution method result interpretation main claim
| # | sentence | role | the authors' own work | states the main conclusion | strength |
|---|---|---|---|---|---|
| s0 | Connections between relations in relation extraction, which we call class ties, are common. | background 1.00 | 0.09 | 0.03 | asserted 1.00 |
| s1 | In distantly supervised scenario, one entity tuple may have multiple relation facts. | background 1.00 | 0.09 | 0.02 | hedged possibility 0.86 |
| s2 | Exploiting class ties between relations of one entity tuple will be promising for distantly supervised relation extraction. | background 0.91 | 0.09 | 0.12 | hedged possibility 0.92 |
| s3 | However, previous models are not effective or ignore to model this property. | gap 1.00 | 0.04 | 0.03 | asserted 1.00 |
| s4 | In this work, to effectively leverage class ties, we propose to make joint relation extraction with a unified model that integrates convolutional neural network (CNN) with a general pairwise ranking framework, in which three novel ranking loss functions are introduced. | method 0.71 | 0.92 | 0.10 | asserted 0.97 |
| s5 | Additionally, an effective method is presented to relieve the severe class imbalance problem from NR (not relation) for model training. | method 0.62 | 0.89 | 0.03 | asserted 0.98 |
| s6 | Experiments on a widely used dataset show that leveraging class ties will enhance extraction and demonstrate the effectiveness of our model to learn class ties. | result 0.95 | 0.94 | 0.31 | asserted 1.00 |
| s7 | Our model outperforms the baselines significantly, achieving state-of-the-art performance. | result 1.00 | 0.95 | 0.64 | asserted 1.00 |
What was examined, and what was not
- arXiv listing abstract v4
- full text
- figures and tables
- references and citing sentences
- relations to other papers
- P abstract
- S sections
- T body sentences
- C citations
- R cross-paper relations
The paper
Original abstract
Connections between relations in relation extraction, which we call class ties, are common. In distantly supervised scenario, one entity tuple may have multiple relation facts. Exploiting class ties between relations of one entity tuple will be promising for distantly supervised relation extraction. However, previous models are not effective or ignore to model this property. In this work, to effectively leverage class ties, we propose to make joint relation extraction with a unified model that integrates convolutional neural network (CNN) with a general pairwise ranking framework, in which three novel ranking loss functions are introduced. Additionally, an effective method is presented to relieve the severe class imbalance problem from NR (not relation) for model training. Experiments on a widely used dataset show that leveraging class ties will enhance extraction and demonstrate the effectiveness of our model to learn class ties. Our model outperforms the baselines significantly, achieving state-of-the-art performance.
Human review
How the literature uses it
3 arXiv papers cite this in 3 sentences
Papers citing it · 2 sentences without a confident label
Cites it as background 1 paper
-
At the algorithm level, for most existing relation extraction models [ref] , the input to the model is a raw sentence with two marked mentions, and the output is whether a relation holds between the two mentions.
Entity-Relation Extraction as Multi-Turn Question Answering · Introduction · 0.98
Discussion
Know something about this paper? Leave a comment, or highlight any passage above to comment on it.