Kernel Methods for Relation Extraction

By Dmitry Zelenko, Chinatsu Aone, Anthony Richardella. 2002

1,311 citations recorded by the source corpus.

We present an application of kernel methods to extracting relations from unstructured natural language sources. We introduce kernels defined over shallow parse representations of text, and design efficient algorithms for computing the kernels. We use the devised kernels in conjunction with Support Vector Machine and Voted Perceptron learning algorithms for the task of extracting person-affiliation and organization-location relations from text. We experimentally evaluate the proposed methods and compare them with feature-based learning algorithms, with promising results.

Subfields: Artificial Intelligence, Natural Language Processing

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

Citations in the corpus

Learning to Reason Deductively: Math Word Problem Solving as Complex Relation Extraction (2022, background): “Our approach is also related to relation extraction (RE) (Zelenko et al., 2003), a fundamental task in the ﬁeld of information extraction that is focused on identifying the relationships between a pair of entities.”
Position-aware Attention and Supervised Data Improve Slot Filling (2017, background): “There are broadly three main lines of work on relation extraction: ﬁrst, fully-supervised approaches (Zelenko et al., 2003; Bunescu and Mooney, 2005), where a statistical classiﬁer is trained on an annotated dataset; second, distant supervision (Mintz et al., 2009; Surdeanu et al., 2012), where a…”
Concept Bottleneck Models (2020, background): “, 2018), parse trees (Zelenko et al., 2003; Bunescu & Mooney, 2005), or natural language explanations (Murty et al.”
Continual Few-shot Relation Learning via Embedding Space Regularization and Data Augmentation (2022, methodology): “Conventional RE methods include supervised (Zelenko et al., 2002; Liu et al., 2013; Zeng et al., 2014; Miwa and Bansal, 2016), semi-supervised (Chen et al.”
Continual Relation Learning via Episodic Memory Activation and Reconsolidation (2020, methodology): “The conventional RE work, including both supervised RE models (Zelenko et al., 2003; Zhou 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…”
FewRel: A Large-Scale Supervised Few-Shot Relation Classification Dataset with State-of-the-Art Evaluation (2018, methodology): “Many works have been proposed for this task, including kernel methods (Zelenko et al., 2002; Mooney and Bunescu, 2006), embedding methods (Gormley et al.”
Classifying Relations via Long Short Term Memory Networks along Shortest Dependency Paths (2015, methodology): “Traditional relation classiﬁcation approaches rely largely on feature representation (Kambhatla, 2004), or kernel design (Zelenko et al., 2003; Bunescu and Mooney, 2005).”
End-to-End Relation Extraction using LSTMs on Sequences and Tree Structures (2016, methodology): “For relation classification, in addition to traditional feature/kernel-based approaches (Zelenko et al., 2003; Bunescu and Mooney, 2005), several neural models have been proposed in the SemEval2010 Task 8 (Hendrickx et al.”
Training a Multilingual Sportscaster: Using Perceptual Context to Learn Language (2014, background): “Recently, kernels over strings and trees have been effectively applied to a variety of problems in text learning and NLP (Lodhi, Saunders, Shawe-Taylor, Cristianini, & Watkins, 2002; Zelenko, Aone, & Richardella, 2003; Collins, 2002; Bunescu & Mooney, 2005).”
Graph Convolution over Pruned Dependency Trees Improves Relation Extraction (2018, methodology): “We note that this relation extraction model is conceptually similar to graph kernel-based models (Zelenko et al., 2003), in that it aims to utilize local dependency tree patterns to inform relation classification.”
Neural Snowball for Few-Shot Relation Learning (2019, methodology): “Supervised RE Early work for fully-supervised RE uses kernel methods (Zelenko et al., 2003; Zhou et al., 2005) and embedding methods (Gorm-ley et al., 2015) to leverage syntactic information to predict relations.”
Reinforcement Learning for Relation Classification From Noisy Data (2018, methodology): “Many approaches have been developed, particularly with supervised methods (Mooney and Bunescu 2005; Zhou et al. 2005; Zelenko, Aone, and Richardella 2003).”
Multi-Level Matching and Aggregation Network for Few-Shot Relation Classification (2019, background): “Some conventional relation classiﬁcation meth-ods (Bethard and Martin, 2007; Zelenko et al., 2002) adopted supervised training and suffered from the lack of large-scale manually labeled data.”
A Shortest Path Dependency Kernel for Relation Extraction (2005, methodology): “The authors use a generalized version of the tree kernel from (Zelenko et al., 2003) to compute a kernel over relation examples, where a relation example consists of the smallest dependency tree containing the two entities of the relation.”
Structured Lexical Similarity via Convolution Kernels on Dependency Trees (2011, background): “…and Duffy, 2002; Kudo and Matsumoto, 2003; Cumby and Roth, 2003; Cancedda et al., 2003; Daum´e III and Marcu, 2004; Toutanova et al., 2004; Shen et al., 2003; Gliozzo et al., 2005; Kudo et al., 2005; Titov and Henderson, 2006; Zelenko et al., 2002; Bunescu and Mooney, 2005; Zhang et al., 2006).”
A Comprehensive Survey on Automatic Knowledge Graph Construction (2023, methodology): “Here, Mulwad et al. [122] develop a model based on SVMRanker that determines which potential nodes can link to a target entity.”
Entity Linking with a Knowledge Base: Issues, Techniques, and Solutions (2015, background): “For example, relation extraction is the process of discovering useful relationships between entities mentioned in text [8], [9], [10], [11], and the extracted relation requires the process ofmapping entities associatedwith the relation to the knowledge base before it could be populated into the know”
DSGAN: Generative Adversarial Training for Distant Supervision Relation Extraction (2018, background): “The goal of relation extraction sys-tem is to predict relation between entity pair in a sentence (Zelenko et al., 2003; Bunescu and Mooney, 2005; GuoDong et al., 2005).”
Tree Edit Models for Recognizing Textual Entailments, Paraphrases, and Answers to Questions (2010, methodology): “When the CTK is applied to relation extraction by Culotta and Sorensen (2004), each subtree is the smallest common subtree that includes the entities between which a relation may exist (e.g., the subtree for Texas-based energy company Exxon Mobil when extracting ORGANIZATION-LOCATION relations).”