Espresso: Leveraging Generic Patterns for Automatically Harvesting Semantic Relations

By Patrick Pantel, Marco Pennacchiotti. Annual Meeting of the Association for Computational Linguistics, 2006

678 citations recorded by the source corpus.

In this paper, we present Espresso, a weakly-supervised, general-purpose, and accurate algorithm for harvesting semantic relations. The main contributions are: i) a method for exploiting generic patterns by filtering incorrect instances using the Web; and ii) a principled measure of pattern and instance reliability enabling the filtering algorithm. We present an empirical comparison of Espresso with various state of the art systems, on different size and genre corpora, on extracting various general and specific relations. Experimental results show that our exploitation of generic patterns substantially increases system recall with small effect on overall precision.

View Paper: https://www.semanticscholar.org/paper/45bc2636d9f5ee728bccebecbd8db0033afd7de3

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Zhiyuan Liu
2. Percy Liang
3. Xu Han
4. Mohit Bansal
5. Maosong Sun
6. Yoshua Bengio
7. Yankai Lin
8. Jianfeng Gao

Citations in the corpus

• Deriving a Web-Scale Common Sense Fact Database (2011, methodology): “Matuszek et al. (2005) used Web search engines to extend Cyc.”
• SemEval-2012 Task 2: Measuring Degrees of Relational Similarity (2012, methodology): “Due to the large number of annotations needed, we used Amazon Mechanical Turk (MTurk),2 which is a popular choice in computational linguistics for gathering large numbers of human responses to linguistic questions (Snow et al., 2008; Mohammad and Turney, 2010).”
• Osprey: Weak Supervision of Imbalanced Extraction Problems without Code (2019, background): “t to method y - |T Px | |T Py | (similar to the relative-recall definition of [16])”
• DELIS Dynamically Evolving , Large-scale Information Systems Integrated Project Member of the FET Proactive Initiative Complex Systems DELIS-TR-594 Yago : A Large Ontology from Wikipedia and WordNet (2007, methodology): “These approaches use information extraction technologies that include pattern matching, natural-language parsing, and statistical learning [137, 65, 27, 2, 128, 116, 50].”
• Distributional semantics in linguistic and cognitive research (2008, background): “…to design algorithms for distributional semantics that are able to identify the particular type of relation linking word meanings (cf. for instance Pantel & Pennacchiotti 2006), but these models are still far from being really satisfactory, let alone to achieve a good level of cognitive…”
• Random Walk Inference and Learning in A Large Scale Knowledge Base (2011, background): “Although there is a great deal of recent research on extracting knowledge from text (Agichtein and Gravano, 2000; Etzioni et al., 2005; Snow et al., 2006; Pantel and Pennacchiotti, 2006; Banko et al., 2007; Yates et al., 2007), much less progress has been made on the problem of drawing reliable infe”
• Towards Understanding Gender Bias in Relation Extraction (2019, methodology): “, 2003), or semi-supervised (Brin, 1998; Agichtein and Gravano, 2000; Etzioni et al., 2005; Pantel and Pennacchiotti, 2006), or purely unsupervised (Etzioni et al.”
• Neural Snowball for Few-Shot Relation Learning (2019, background): “(Riloff et al., 1999; Etzioni et al., 2005; Pantel and Pennacchiotti, 2006; Rozenfeld and Feldman, 2008; Nakashole et al., 2011).”
• Extracting Diurnal Patterns of Real World Activity from Social Media (2013, background): “Pantel and Pennacchiotti (2006) discovered new forms of semantic relations by starting with a small seed list and expanding it.”
• Reducing Wrong Labels in Distant Supervision for Relation Extraction (2012, methodology): “Bootstrapping for relation extraction (Riloff and Jones, 1999; Pantel and Pennacchiotti, 2006; Carl-son et al., 2010) is related to our method.”
• Recovering Semantics of Tables on the Web (2011, methodology): “Existing methods for extracting classes of instances from the Web require sets of instances that are each either unlabeled [18, 23, 29], or associated with a class label [1, 13, 21, 22, 30].”
• YAGO: A Large Ontology from Wikipedia and WordNet (2008, methodology): “These approaches use information extraction technologies that include pattern matching, natural-language parsing, and statistical learning [49,25,11,1,46,41,18].”
• Distributional Memory: A General Framework for Corpus-Based Semantics (2010, unknown): “The two words can be concatenated, treating the links as basis elements, in order to model relational similarity (Pantel and Pennacchiotti 2006; Turney 2006b).”
• Understanding the Semantic Structure of Noun Phrase Queries (2010, background): “Web users, however, rarely express their intent in full language.”
• Continual Relation Learning via Episodic Memory Activation and Reconsolidation (2020, background): “…and Titov, 2016), relation clustering (Shinyama and Sekine, 2006; Elsahar et al., 2017; Wu et al., 2019), and data collection (Riloff et al., 1999; Et-zioni et al., 2005; Pantel and Pennacchiotti, 2006; Rozenfeld and Feldman, 2008; Nakashole et al., 2011; Zhu et al., 2009; Gao et al., 2020).”