Learning Entailment Rules for Unary Templates

By Idan Szpektor, Ido Dagan. 2008

123 citations recorded by the source corpus.

Most work on unsupervised entailment rule acquisition focused on rules between templates with two variables, ignoring unary rules - entailment rules between templates with a single variable. In this paper we investigate two approaches for unsupervised learning of such rules and compare the proposed methods with a binary rule learning method. The results show that the learned unary rule-sets outperform the binary rule-set. In addition, a novel directional similarity measure for learning entailment, termed Balanced-Inclusion, is the best performing measure.

Subfields: Artificial Intelligence, Information Systems, 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 Information Systems

In Natural Language Processing

Citations in the corpus

From image descriptions to visual denotations: New similarity metrics for semantic inference over event descriptions (2014, background): “More recently, asymmetric similarities have been proposed as more suitable for semantic inference tasks such as entailment (Weeds and Weir, 2003; Szpektor and Dagan, 2008; Clarke, 2009; Kotlerman et al., 2010).”
Learning Entailment Relations by Global Graph Structure Optimization (2012, methodology): “To remedy that, Szpektor and Dagan (2008) suggested a directional distributional similarity measure.”
Crowdsourcing Inference-Rule Evaluation (2012, methodology): “Lastly, we computed the area under the recall-precision curve (AUC) for DIRT , Cover , BInc and Berant et al. ’s method, resulting in an AUC of 0.4, 0.43, 0.44, and 0.52 respectively.”
A Survey of Paraphrasing and Textual Entailment Methods (2009, methodology): “…extraction methods indirectly, for example by measuring how much the extracted pairs help in information extraction (Bhagat & Ravichandran, 2008; Szpektor & Dagan, 2007, 2008) or when expanding queries (Pasca & Dienes, 2005), by measuring how well the extracted pairs, seen as paraphrasing…”
Relation Extraction with Matrix Factorization and Universal Schemas (2013, background): “This is similar in spirit to work on learning entailment rules (Szpektor et al., 2004; Zanzotto et al., 2006; Szpektor and Dagan, 2008).”
Directional distributional similarity for lexical inference (2010, methodology): “In a future work, we aim at automatically learning each rule’s context model as well, to improve rule application (Szpektor et al. 2008).”
Knowledge-Based Textual Inference via Parse-Tree Transformations (2015, methodology): “…(Barzilay & McKeown , 2001; Barzilay & Lee, 2003; Pang, Knight, & Marcu, 2003), by querying the Web (Ravichandran & Hovy, 2002; Szpektor et al., 2004), or from a local corpus (Lin & Pantel, 2001; Glickman & Dagan, 2003; Bhagat & Ravichandran, 2008; Szpektor & Dagan, 2008; Yates & Etzioni, 2009).”