Relation Classification via Recurrent Neural Network

By Dongxu Zhang. arXiv.org, 2015

360 citations recorded by the source corpus.

Deep learning has gained much success in sentence-level relation classification. For example, convolutional neural networks (CNN) have delivered competitive performance without much effort on feature engineering as the conventional pattern-based methods. Thus a lot of works have been produced based on CNN structures. However, a key issue that has not been well addressed by the CNN-based method is the lack of capability to learn temporal features, especially long-distance dependency between nominal pairs. In this paper, we propose a simple framework based on recurrent neural networks (RNN) and compare it with CNN-based model. To show the limitation of popular used SemEval-2010 Task 8 dataset, we introduce another dataset refined from MIMLRE(Angeli et al., 2014). Experiments on two different datasets strongly indicates that the RNN-based model can deliver better performance on relation classification, and it is particularly capable of learning long-distance relation patterns. This makes it suitable for real-world applications where complicated expressions are often involved.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/0f36511d47596b91b8d3db265e4ca7bafc0b15a4

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

Refining Sample Embeddings with Relation Prototypes to Enhance Continual Relation Extraction (2021, background): “(2) Recurrent neural networks (RNNs) (Zhang and Wang, 2015; Xu et al., 2015; Zhou et al., 2016; Zhang et al., 2018a) are particularly capable of learning long-distance relation pat-”
Semi-supervised Relation Extraction via Incremental Meta Self-Training (2020, methodology): “We follow the labeling mechanism adopted by Zhang and Wang (2015) (1) The updated sentence is used as the input of the Contextualized Relation Encoder.”
LISA: Explaining Recurrent Neural Network Judgments via Layer-wIse Semantic Accumulation and Example to Pattern Transformation (2018, methodology): “As position features in relation classification experiments, we use position indicators (PI) (Zhang and Wang, 2015) in C-BRNN to annotate target entity/nominals in the word sequence, without necessity to change the input vectors, while it increases the length of the input word sequences, as four ind”
Span-based Joint Entity and Relation Extraction with Transformer Pre-training (2019, methodology): “While common methods tackle the two problems separately [36, 39, 38], more recent work uses joint models for both steps [3, 21].”
Chemical-induced disease relation extraction via convolutional neural network (2017, background): “Zhang and Wang (28) employed a bidirectional RNN framework to learn long-distance relation patterns to tackle the relation classification problem, and Page 2 of 12 Database, Vol.”
Long-tail Relation Extraction via Knowledge Graph Embeddings and Graph Convolution Networks (2019, methodology): “Other neural architectures such as recurrent neural networks (Zhang and Wang, 2015) can also be used as sen-”
Probing Linguistic Features of Sentence-Level Representations in Relation Extraction (2020, methodology): “Bi-LSTM max Similar to Zhang and Wang (2015) and Zhang et al. (2017), we use a Bi-LSTM to encode the input sequence.”
Position-aware Attention and Supervised Data Improve Slot Filling (2017, background): “Existing work on neural relation extraction (e.g., Zeng et al., 2014; Nguyen and Grishman, 2015; Zhou et al., 2016) has focused on convolutional neural networks (CNNs), recurrent neural networks (RNNs), or their combination.”
Matching the Blanks: Distributional Similarity for Relation Learning (2019, positive): “Similarly, by training by matching the blanks and then tuning on labeled data, we signiﬁcantly improve performance on the SemEval 2010 Task 8 (Hen-drickx et al., 2009), KBP-37 (Zhang and Wang, 2015), and TACRED (Zhang et al., 2017) relation extraction benchmarks.”
Attention-Based Bidirectional Long Short-Term Memory Networks for Relation Classification (2016, methodology): “One related work was proposed by Zhang and Wang (2015), which employed bidirectional RNN to learn patterns of relations from raw text data.”
More Data, More Relations, More Context and More Openness: A Review and Outlook for Relation Extraction (2020, neutral): “There are already many datasets that beneﬁt RE research: For supervised RE, there are MUC (Gr-ishman and Sundheim, 1996), ACE-2005 (Ntro-duction, 2005), SemEval-2010 Task 8 (Hendrickx et al., 2009), KBP37 (Zhang and Wang, 2015) and TACRED (Zhang et al., 2017); and we have NYT-10 (Riedel et al., 2010”
Joint entity recognition and relation extraction as a multi-head selection problem (2018, methodology): “CNN- (Zeng et al., 2014; Xu et al., 2015a; dos Santos et al., 2015) and RNN-based (Socher et al., 2013; Zhang & Wang, 2015; Xu et al., 2015b) models have been introduced to automatically extract lexical and sentence level features leading to a deeper language understanding.”
Prototypical Representation Learning for Relation Extraction (2021, methodology): “…networks have gained much attention then, a series of neural supervised models have been proposed (Liu et al., 2013; Zeng et al., 2014; Xu et al., 2015; Santos et al., 2015; Zhang & Wang, 2015; Verga et al., 2016; Verga & McCallum, 2016; Li et al., 2019; Distiawan et al., 2019; Ding et al., 2019).”
Hierarchical Relation Extraction with Coarse-to-Fine Grained Attention (2018, background): “These neural models can accurately capture textual relations without explicit linguistic analysis (Zeng et al., 2014; Xu et al., 2015; Santos et al., 2015; Zhang and Wang, 2015; Verga et al., 2016; Verga and McCallum, 2016).”
Improving Relation Extraction by Pre-trained Language Representations (2019, methodology): “Similarly, our model outperforms approaches that rely on explicit syntactic features such as the shortest dependency path and learned distributed representations of part-of-speech and named entity tags (e.g., BCRNN [Cai et al., 2016], DRNN [Xu et al., 2016], CGCN [Zhang et al., 2018]).”