Discovering Relations among Named Entities from Large Corpora

By Takaaki Hasegawa, Satoshi Sekine, Ralph Grishman. Annual Meeting of the Association for Computational Linguistics, 2004

485 citations recorded by the source corpus.

Discovering the significant relations embedded in documents would be very useful not only for information retrieval but also for question answering and summarization. Prior methods for relation discovery, however, needed large annotated corpora which cost a great deal of time and effort. We propose an unsupervised method for relation discovery from large corpora. The key idea is clustering pairs of named entities according to the similarity of context words intervening between the named entities. Our experiments using one year of newspapers reveals not only that the relations among named entities could be detected with high recall and precision, but also that appropriate labels could be automatically provided for the relations.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/2b4dd276f4a8c1b0ba2670331364f7b4885322b9

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

Citations in the corpus

Relation Extraction with Matrix Factorization and Universal Schemas (2013, background): “Relational Clustering There is a large body of work aiming to discover latent relations by clustering surface patterns (Hasegawa et al., 2004; Shinyama and Sekine, 2006; Kok and Domingos, 2008; Yao et al., 2011; Takamatsu et al., 2011), or by inducing relationships between patterns independently of…”
Relation Classification via Convolutional Deep Neural Network (2014, methodology): “Hasegawa et al. (2004) adopted a hierarchical clustering method to cluster the contexts of nominals and simply selected the most frequent words in the contexts to represent the relation between the nominals.”
Relation Extraction Using Label Propagation Based Semi-Supervised Learning (2006, background): “…e.g., supervised learning algorithms (Miller et al., 2000; Zelenko et al., 2002; Culotta and Soresen, 2004; Kambhatla, 2004; Zhou et al., 2005), semi-supervised learning algorithms (Brin, 1998; Agichtein and Gravano, 2000; Zhang, 2004), and unsupervised learning algorithms (Hasegawa et al., 2004).”
Generative Event Schema Induction with Entity Disambiguation (2015, methodology): “More recently, work after (Hasegawa et al., 2004) has developed weakly supervised forms of Information Extraction including schema induction in their objectives.”
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”
Learning Syntactic Patterns for Automatic Hypernym Discovery (2004, background): “Thus a wide variety of recent research has focused on finding methods for automatically learning taxonomic relations and constructing semantic hierarchies [1, 2, 3, 4, 6, 8, 9, 10, 16, 18, 19, 20, 21, 22].”
Using Corpus Statistics on Entities to Improve Semi-supervised Relation Extraction from the Web (2007, background): “Another direction for unsupervised relation learning was taken in (Hasegawa, Sekine et al. 2004; Chen, Ji et al. 2005).”
Preemptive Information Extraction using Unrestricted Relation Discovery (2006, unknown): “Hasegawa et al. (2004) tried to extract multiple relations by choosing entity types.”
Relation Classification via Multi-Level Attention CNNs (2016, methodology): “Apart from a few unsupervised clustering meth-ods (Hasegawa et al., 2004; Chen et al., 2005), the majority of work on relation classiﬁcation has been supervised, typically cast as a standard multi-class or multi-label classiﬁcation task.”
Mining knowledge from text using information extraction (2005, unknown): “Although some work has been done in this area [19; 36 ], this is another promising area for future research.”