Classifying Relations via Long Short Term Memory Networks along Shortest Dependency Paths

By Yan Xu, Lili Mou, Ge Li, Yunchuan Chen, Hao Peng, Zhi Jin. 2015

691 citations recorded by the source corpus.

Relation classification is an important research arena in the field of natural language processing (NLP). In this paper, we present SDP-LSTM, a novel neural network to classify the relation of two entities in a sentence. Our neural architecture leverages the shortest dependency path (SDP) between two entities; multichannel recurrent neural networks, with long short term memory (LSTM) units, pick up heterogeneous information along the SDP. Our proposed model has several distinct features: (1) The shortest dependency paths retain most relevant information (to relation classification), while eliminating irrelevant words in the sentence. (2) The multichannel LSTM networks allow effective information integration from heterogeneous sources over the dependency paths. (3) A customized dropout strategy regularizes the neural network to alleviate overfitting. We test our model on the SemEval 2010 relation classification task, and achieve an $F_1$-score of 83.7\%, higher than competing methods in the literature.

Subfields: Artificial Intelligence, Natural Language Processing, Model Architectures

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

In Natural Language Processing

In Model Architectures

Citations in the corpus

Revisiting LSTM Networks for Semi-Supervised Text Classification via Mixed Objective Function (2019, background): “Table 10: Model performance on TACRED and SemEval datasets; P = Precision; R = Recall; aSantos, Xiang, and Zhou (2015); bXu et al. (2015); cZhang et al.”
Natural Language Inference by Tree-Based Convolution and Heuristic Matching (2015, methodology): “Concatenation is also applied in our previous work of matching the subject and object in relation classification (Xu et al., 2015; Xu et al., 2016).”
Natural Language Processing for EHR-Based Computational Phenotyping (2018, background): “tion [146], semantic analysis [147], [148], information retrieval [149], [150], entity recognition [151], [152], relation extraction [153], [154], [155], [156], and event detection [157], [158].”
Recurrent Neural Networks for Classifying Relations in Clinical Notes (2017, neutral): “Our models differ from general domain relation classification models [37,38], in that we do not use syntactic/ semantic resources (compared to Yan et al.”
Continual Relation Learning via Episodic Memory Activation and Reconsolidation (2020, background): “…et al., 2005; Gormley et al., 2015; Socher et al., 2012; Liu et al., 2013; Zeng et al., 2014; Nguyen and Grishman, 2015; dos Santos et al., 2015; Xu et al., 2015; Liu et al., 2015; Miwa and Bansal, 2016) and distantly supervised models (Bunescu and Mooney, 2007; Mintz et al., 2009; Riedel et…”
Attention-Based Bidirectional Long Short-Term Memory Networks for Relation Classification (2016, background): “Attentive neural networks have recently demonstrated success in a wide range of tasks ranging from question answering, machine translations, speech recognition, to image captioning (Hermann et al., 2015; Bahdanau et al., 2014; Chorowski et al., 2015; Xu et al., 2015).”
Neural Snowball for Few-Shot Relation Learning (2019, background): “Besides, dependency parsing trees have also been proved to be efﬁcient in RE (Xu et al., 2015; Liu et al., 2015; Miwa and Bansal, 2016).”
A Multi-Channel Deep Neural Network for Relation Extraction (2020, methodology): “[13] implemented a recursive neural network(RNN) model along the shortest dependency path between two named entities.”
Chemical-induced disease relation extraction via convolutional neural network (2017, methodology): “Apart from the contextual features, we argue that the dependency associations can offer more concise and effective information to determine CID relations between entity mentions as in other domains (29).”
A neural joint model for entity and relation extraction from biomedical text (2017, methodology): “For relation classification, there are two state-of-the-art methods using deep neural networks, namely RNNs [24] and convolutional neural networks (CNNs) [25].”
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).”
Distilling Word Embeddings: An Encoding Approach (2015, methodology): “To set up our experiments, we leveraged two state-of-theart neural models: a tree-based convolutional neural network (TBCNN) for sentiment analysis [10], and a long short term memory-based recurrent network along shortest dependency path (SDP-LSTM)(3) between two entities for relation classification”
Cross-Sentence N-ary Relation Extraction with Graph LSTMs (2017, methodology): “directly applicable. 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). Table 1 shows the results for cross-sentence, ternary relation extraction. All ne”