Semantic Relation Classification via Convolutional Neural Networks with Simple Negative Sampling

By Kun Xu, Yansong Feng, Songfang Huang, Dongyan Zhao. Conference on Empirical Methods in Natural Language Processing, 2015

303 citations recorded by the source corpus.

Syntactic features play an essential role in identifying relationship in a sentence. Previous neural network models directly work on raw word sequences or constituent parse trees, thus often suffer from irrelevant information introduced when subjects and objects are in a long distance. In this paper, we propose to learn more robust relation representations from shortest dependency paths through a convolution neural network. We further take the relation directionality into account and propose a straightforward negative sampling strategy to improve the assignment of subjects and objects. Experimental results show that our method outperforms the state-of-theart approaches on the SemEval-2010 Task 8 dataset.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/84af5095e7269d6ed70de78e2c0027ff6aab4d42

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

Relation Classification via Recurrent Neural Network (2015, background): “, 2015) and NS-depLCNN(Xu et al., 2015a) been proposed recently, which are all based on CNN structure.”
Reasoning with Latent Structure Refinement for Document-Level Relation Extraction (2020, methodology): “The shortest dependency path has been widely used in the sentence-level relation extraction as it is able to effectively make use of relevant information while ignoring irrelevant information (Bunescu and Mooney, 2005; Xu et al., 2015a,b).”
Graph Convolution over Pruned Dependency Trees Improves Relation Extraction (2018, methodology): “Another popular approach, inspired by Bunescu and Mooney (2005), is to reduce the parse tree to the shortest dependency path between the entities (Xu et al., 2015a,b).”
Position-aware Attention and Supervised Data Improve Slot Filling (2017, methodology): “Other popular approaches include using CNN or RNN over dependency paths between entities (Xu et al., 2015a,b), augmenting RNNs with different components (Xu et al., 2016; Zhou et al., 2016), and combining RNNs and CNNs (Vu et al., 2016; Wang et al., 2016).”
Relation Extraction with Multi-instance Multi-label Convolutional Neural Networks (2016, methodology): “Recent studies have shown promising results on using deep neural networks for automatic feature extraction (Zeng et al., 2014; Liu et al., 2015; Xu et al., 2015).”
A general framework for information extraction using dynamic span graphs (2019, background): “Many state-of-the-art RE models rely upon domain-speciﬁc external syntactic tools to construct dependency paths between the entities in a sentence (Li and Ji, 2014; Xu et al., 2015; Miwa and Bansal, 2016; Zhang et al., 2017).”
Question Answering on Freebase via Relation Extraction and Textual Evidence (2016, methodology): “…in KB question-answering (Yih et al., 2015; Dong et al., 2015), and the success of syntactic dependencies for relation extraction (Liu et al., 2015; Xu et al., 2015), we propose a Multi-Channel Convolutional Neural Network (MCCNN) which could exploit both syntactic and sentential information for…”
Attention Guided Graph Convolutional Networks for Relation Extraction (2019, methodology): “…(Zhang et al., 2018) 69.9 63.3 66.4 AGGCN (ours) 69.9 60.9 65.1 C-AGGCN (ours) 73.1 64.2 68.2 Model F1 SVM (Rink and Harabagiu, 2010) 82.2 SDP-LSTM (Xu et al., 2015c) 83.7 SPTree (Miwa and Bansal, 2016) 84.4 PA-LSTM (Zhang et al., 2017) 82.7 C-GCN (Zhang et al., 2018) 84.8 C-AGGCN (ours) 85.7…”
Extracting Multiple-Relations in One-Pass with Pre-Trained Transformers (2019, methodology): “Existing MRE approaches are based on either feature and model architecture selection techniques (Xu et al., 2015; Gormley et al., 2015; Nguyen and Grishman, 2015; F. Petroni and Gemulla, 2015; Sorokin and Gurevych, 2017; Song et al., 2018b), or domain adaptations approaches (Fu et al.”
More Data, More Relations, More Context and More Openness: A Review and Outlook for Relation Extraction (2020, methodology): “Xu et al. (2015a) and Xu et al. (2015b) adopt CNNs and RNNs over shortest dependency paths respectively.”
Going out on a limb: Joint Extraction of Entity Mentions and Relations without Dependency Trees (2017, methodology): “There have been several models proposed including featurebased models (Bunescu and Mooney, 2005; Zelenko et al., 2003) and neural network based models (Socher et al., 2012; dos Santos et al., 2015; Hashimoto et al., 2015; Xu et al., 2015a,b).”
Cross-Sentence N-ary Relation Extraction with Graph LSTMs (2017, background): “So we also compared with a state-of-the-art tree LSTM system (Miwa and Bansal, 2016) and a BiLSTM on the shortest dependency path between the two entities (BiLSTM-Shortest-Path) (Xu et al., 2015b).”
Improving Relation Extraction by Pre-trained Language Representations (2019, background): “Xu et al. [2015a,b] integrated shortest dependency path (SDP) information into a LSTM-based relation classiﬁcation model.”
Joint Extraction of Entities and Relations Based on a Novel Tagging Scheme (2017, methodology): “Existing methods for relation classiﬁcation can also be divided into handcrafted feature based methods (Rink, 2010; Kambhatla, 2004) and neural network based methods (Xu, 2015a; Zheng et al., 2016; Zeng, 2014; Xu, 2015b; dos Santos, 2015).”
Extracting Relational Facts by an End-to-End Neural Model with Copy Mechanism (2018, methodology): “Although great progresses have been made (Hendrickx et al., 2010; Zeng et al., 2014; Xu et al., 2015a,b), they all assume that the entities are identiﬁed beforehand and neglect the extraction of entities.”