A Shortest Path Dependency Kernel for Relation Extraction
By Razvan C. Bunescu, Raymond J. Mooney. 2005
1,040 citations recorded by the source corpus.
We present a novel approach to relation extraction, based on the observation that the information required to assert a relationship between two named entities in the same sentence is typically captured by the shortest path between the two entities in the dependency graph. Experiments on extracting top-level relations from the ACE (Automated Content Extraction) newspaper corpus show that the new shortest path dependency kernel outperforms a recent approach based on dependency tree kernels.
Subfields: Artificial Intelligence, Information Extraction
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
- Mohit Bansal
- Percy Liang
- Christopher D. Manning
- Luke S. Zettlemoyer
- Yejin Choi
- Zhiyuan Liu
- Jianfeng Gao
- Yoav Goldberg
In Information Extraction
- Yuan Luo
- Christopher D. Manning
- Thien Huu Nguyen
- Ralph Grishman
- Alessandro Moschitti
- Ozlem Uzuner
- Gabor Angeli
- Peter Szolovits
Citations in the corpus
- 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.”
- Concept Bottleneck Models (2020, background): “…concepts commonly use them in auxiliary objectives in a multi-task setup, or as auxiliary features; examples include using object parts (Huang et al., 2016; Zhou et al., 2018), parse trees (Zelenko et al., 2003; Bunescu & Mooney, 2005), or natural language explanations (Murty et al., 2020).”
- 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 SemEval-2010 Task 8 (Hendrickx et al., 2010), including embedding-based models (Hashimoto et al., 2015), CNN-based…”
- Graph Convolution over Pruned Dependency Trees Improves Relation Extraction (2018, background): “, 2003) and dependency path-based kernels (Bunescu and Mooney, 2005) are effective for this task.”
- Attention-Based Bidirectional Long Short-Term Memory Networks for Relation Classification (2016, background): “Traditional relation classification methods that employ handcrafted features from lexical resources, are usually based on pattern matching, and have achieved high performance (Bunescu and Mooney, 2005; Mintz et al., 2009; Rink and Harabagiu, 2010).”
- Probing Linguistic Features of Sentence-Level Representations in Relation Extraction (2020, neutral): “dependency path information (Bunescu and Mooney, 2005; Krause et al., 2012; Mintz et al., 2009), or part-of-speech”
- 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).”
- Using Sequence Kernels to identify Opinion Entities in Urdu (2011, background): “For example, in the task of relation extraction, features included in the shortest path between the mentions of the two sequences (which hold the relation) play a decisive role (Bunescu and Mooney, 2005).”
- Open Information Extraction from the Web (2007, background): “[Bunescu and Mooney, 2005], maximum-entropy models [Kambhatla, 2004], graphical models [Rosario and Hearst, 2004; Culotta et al. , 2006], and co-occurrence statistics [Lin and Pantel, 2001; Ciaramita et al. , 2005] over small, domain-specific corpora and limited sets of relations.”
- Attention Guided Graph Convolutional Networks for Relation Extraction (2019, background): “, 2016), whereas dependencybased models incorporate dependency trees into the models (Bunescu and Mooney, 2005; Peng et al., 2017).”
- Going out on a limb: Joint Extraction of Entity Mentions and Relations without Dependency Trees (2017, methodology): “There have been several models proposed including feature-based models (Bunescu and Mooney, 2005; Ze-lenko 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).”
- 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).”