Dependency Tree Kernels for Relation Extraction

By Aron Culotta, Jeffrey Scott Sorensen. 2004

934 citations recorded by the source corpus.

We extend previous work on tree kernels to estimate the similarity between the dependency trees of sentences. Using this kernel within a Support Vector Machine, we detect and classify relations between entities in the Automatic Content Extraction (ACE) corpus of news articles. We examine the utility of different features such as Wordnet hypernyms, parts of speech, and entity types, and find that the dependency tree kernel achieves a 20% F1 improvement over a "bag-of-words" kernel.

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

Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations (2016, methodology): “It is similar to the format used in knowledge bases in NLP.”
Visual Relationship Detection with Language Priors (2016, methodology): “ual relationship detection, we introduce a new dataset that contains 5000 images with 37;993 relationships. Existing datasets that contain relationships were designed 1 In natural language processing [2,3,4,5], relationships are dened as hsubject - predicate - objecti. In this paper, we dene them as”
Classification with class imbalance problem: A review (2015, neutral): “[127] Dependency tree kernels”
Incremental Joint Extraction of Entity Mentions and Relations (2014, background): “, (Reichartz et al., 2009; Sun et al., 2011; Jiang and Zhai, 2007; Bunescu and Mooney, 2005; Zhao and Grishman, 2005; Culotta and Sorensen, 2004; Zhou et al., 2007; Qian and Zhou, 2010; Qian et al., 2008; Chan and Roth, 2011; Plank and Moschitti, 2013)) have drawn much attention in recent years but ”
Visual Relationship Detection with Internal and External Linguistic Knowledge Distillation (2017, background): “Relationships are commonly defined as tuples consisting of a subject (subj), predicate (pred) and object (obj) [31, 8, 1].”
Efficient Convolution Kernels for Dependency and Constituent Syntactic Trees (2006, background): “(2) Such kernel generates a richer feature space than those defined in [7, 2, 3, 5, 13].”
Extracting Relations with Integrated Information Using Kernel Methods (2005, background): “Culotta and Sorensen (2004) described a slightly generalized version of this kernel based on dependency trees.”
Non-Projective Dependency Parsing using Spanning Tree Algorithms (2005, background): “Dependency parsing has seen a surge of interest lately for applications such as relation extraction (Culotta and Sorensen, 2004), machine translation (Ding and Palmer, 2005), synonym generation (Shinyama et al., 2002), and lexical resource augmentation (Snow et al., 2004).”
Exploiting Shallow Linguistic Information for Relation Extraction from Biomedical Literature (2006, background): “Different works (Gliozzo et al., 2005; Zhao and Grishman, 2005; Culotta and Sorensen, 2004) empirically demonstrate the effectiveness of combining kernels in this way, showing that the combined kernel always improves the performance of the individual ones.”
KERMIT: Complementing Transformer Architectures with Encoders of Explicit Syntactic Interpretations (2020, positive): “Structural kernels have been deﬁned for both constituency-based (Collins and Duffy, 2002; Moschitti, 2006) and dependency-based parse trees (Culotta and Sorensen, 2004).”
More Data, More Relations, More Context and More Openness: A Review and Outlook for Relation Extraction (2020, neutral): “Due to the wide use of support vector machines (SVM), kernel-based methods have been widely explored, which design kernel functions for SVM to measure the similarities between relation representations and textual instances (Culotta and Sorensen, 2004; Bunescu and Mooney, 2005; Zhao and Grishman, 200”
Combining Lexical, Syntactic, and Semantic Features with Maximum Entropy Models for Information Extraction (2004, background): “The reader is referred to (Florian et al., 2004; Ittycheriah et al., 2003; Luo et al., 2004) for more details of our mention detection and mention chaining modules.”
Tree Kernel-Based Relation Extraction with Context-Sensitive Structured Parse Tree Information (2007, methodology): “This makes it suffer from the similar behavior with that of Culotta and Sorensen (2004): high precision but very low recall.”
Relation Extraction: Perspective from Convolutional Neural Networks (2015, methodology): “…2005; Jiang and Zhai, 2007; Chan and Roth, 2010; Sun et al., 2011; Nguyen and Grishman, 2014) and the kernel-based method (Zelenko et al., 2003; Culotta and Sorensen, 2004; Bunescu and Mooney, 2005a; Bunescu and Mooney, 2005b; Zhang et al., 2006; Zhou et al., 2007; Qian et al., 2008; Nguyen et…”
Generating Image Descriptions Using Dependency Relational Patterns (2010, methodology): “In information extraction, for instance, dependency patterns have been used to extract relevant information from text resources (Yangarber et al., 2000; Sudo et al., 2001; Culotta and Sorensen, 2004; Stevenson and Greenwood, 2005; Bunescu and Mooney, 2005; Stevenson and Greenwood, 2009).”
Tree Kernels for Semantic Role Labeling (2008, methodology): “To measure the similarity between two nodes, the contiguous string kernel and the sparse string kernel were used.”