Exploring Various Knowledge in Relation Extraction
By Guodong Zhou, Jian Su, Jie Zhang, Min Zhang. 2005
865 citations recorded by the source corpus.
Extracting semantic relationships between entities is challenging. This paper investigates the incorporation of diverse lexical, syntactic and semantic knowledge in feature-based relation extraction using SVM. Our study illustrates that the base phrase chunking information is very effective for relation extraction and contributes to most of the performance improvement from syntactic aspect while additional information from full parsing gives limited further enhancement. This suggests that most of useful information in full parse trees for relation extraction is shallow and can be captured by chunking. We also demonstrate how semantic information such as WordNet and Name List, can be used in feature-based relation extraction to further improve the performance. Evaluation on the ACE corpus shows that effective incorporation of diverse features enables our system outperform previously best-reported systems on the 24 ACE relation subtypes and significantly outperforms tree kernel-based systems by over 20 in F-measure on the 5 ACE relation types.
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
- Zhiyuan Liu
- Maosong Sun
- Mohit Bansal
- Luke S. Zettlemoyer
- Jianfeng Gao
- Percy Liang
- Yoav Goldberg
- Caiming Xiong
In Information Extraction
Citations in the corpus
- Distant supervision for relation extraction without labeled data (2009, methodology): “…a wide variety of lexical, syntactic, and semantic features, and use supervised classifiers to label the relation mention holding between a given pair of entities in a test set sentence, optionally combining relation mentions (Zhou et al., 2005; Zhou et al., 2007; Sur-deanu and Ciaramita, 2007).”
- 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…”
- Matching the Blanks: Distributional Similarity for Relation Learning (2019, background): “In a first group, supervised (Kambhatla, 2004; GuoDong et al., 2005; Zeng et al., 2014), or distantly supervised relation extractors (Mintz et al.”
- Classifying Relations via Long Short Term Memory Networks along Shortest Dependency Paths (2015, background): “, hypernyms versus named-entity tags), and thus it is hard to improve performance in this way (GuoDong et al., 2005).”
- End-to-End Relation Extraction using LSTMs on Sequences and Tree Structures (2016, background): “…tasks, i.e., named entity recognition (NER) (Nadeau and Sekine, 2007; Ratinov and Roth, 2009) and relation extraction (Zelenko et al., 2003; Zhou et al., 2005), but recent studies show that end-to-end (joint) modeling of entity and relation is important for high performance (Li and Ji,…”
- 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”
- Improved Neural Relation Detection for Knowledge Base Question Answering (2017, methodology): “Traditional RE methods rely on large amount of hand-crafted features (Zhou et al., 2005; Rink and Harabagiu, 2010; Sun et al., 2011).”
- 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.”
- Towards Understanding Gender Bias in Relation Extraction (2019, methodology): “Early on, learning algorithms for relation extraction models were typically categorized as supervised, including feature-based methods (Kambhatla, 2004; Zhou et al., 2005; Zhao and Grishman, 2005) and kernel-”
- Action Genome: Actions As Compositions of Spatio-Temporal Scene Graphs (2019, background): “d relationship labels grounded in actions. Scene graph prediction. Scene graphs are a formal representation for image information [35,42] in a form of a graph, which is widely used in knowledge bases [27, 13,88]. Each scene graph encodes objects as nodes connected together by pairwise relationships ”
- A Brief Survey of Text Mining: Classification, Clustering and Extraction Techniques (2017, methodology): “Many studies using the classification approach for relation extraction have been done such as [25, 26, 59, 72, 77].”
- Going out on a limb: Joint Extraction of Entity Mentions and Relations without Dependency Trees (2017, background): “…broadly categorized into – 1) pipeline models that treat the identification of entity mentions (Nadeau and Sekine, 2007) and relation classification (Zhou et al., 2005) as two separate tasks; and 2) joint models, also the more recent, which simultaneously identify the entity mention and relations…”
- Distant Supervision for Relation Extraction via Piecewise Convolutional Neural Networks (2015, methodology): “Supervised approaches are the most commonly used methods for relation extraction and yield relatively high performance (Bunescu and Mooney, 2006; Zelenko et al., 2003; Zhou et al., 2005).”
- Probing Linguistic Features of Sentence-Level Representations in Relation Extraction (2020, methodology): “Relation extraction literature is rich with information about useful features for the task (Zhou et al., 2005; Mintz et al., 2009; Surdeanu et al., 2011).”
- Cross-Sentence N-ary Relation Extraction with Graph LSTMs (2017, neutral): “ traditional featurebased methods rely on carefully designed features to learn good models, and often integrate diverse sources of evidence such as word sequences and syntax context (Kambhatla, 2004; GuoDong et al., 2005; Boschee et al., 2005; Suchanek et al., 2006; Chan and Roth, 2010; Nguyen and G”
- Improved Relation Extraction with Feature-Rich Compositional Embedding Models (2015, methodology): “(3) A log-linear model with a rich binary feature set from Sun et al. (2011) (Baseline)— this consists of all the baseline features of Zhou et al. (2005) plus several additional carefully-chosen features that have been highly tuned for ACE-style relation extraction over years of research.”
- A Novel Cascade Binary Tagging Framework for Relational Triple Extraction (2019, background): “Early works in relational triple extraction took a pipeline approach (Zelenko et al., 2003; Zhou et al., 2005; Chan and Roth, 2011).”
- Hierarchical Relation Extraction with Coarse-to-Fine Grained Attention (2018, methodology): “Supervised models (Zelenko et al., 2003; Zhou et al., 2005; Mooney and Bunescu, 2006) for RE require adequate amounts of annotated data for their training.”