An extended model of natural logic

Abstract

We propose a model of natural language inference which identifies valid inferences by their lexical and syntactic features, without full semantic interpretation. We extend past work in natural logic, which has focused on semantic containment and monotonicity, by incorporating both semantic exclusion and implicativity. Our model decomposes an inference problem into a sequence of atomic edits linking premise to hypothesis; predicts a lexical semantic relation for each edit; propagates these relations upward through a semantic composition tree according to properties of intermediate nodes; and joins the resulting semantic relations across the edit sequence. A computational implementation of the model achieves 70% accuracy and 89% precision on the FraCaS test suite. Moreover, including this model as a component in an existing system yields significant performance gains on the Recognizing Textual Entailment challenge.

Leveraging Linguistic Structure For Open Domain Information Extraction

“…Prior work has used natural logic for RTE-style textual entailment, as a formalism well-suited for formal semantics in neural networks, and as a framework for common-sense reasoning (MacCartney and Manning, 2009;Watanabe et al, 2012;Bowman et al, 2014;Angeli and Manning, 2013). We adopt the precise semantics of Icard and Moss (2014).…”

A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference

“…In this task, also known as recognizing textual entailment (Cooper et al, 1996;Fyodorov et al, 2000;Condoravdi et al, 2003;Bos and Markert, 2005;Dagan et al, 2006;MacCartney and Manning, 2009), a model is presented with a pair of sentences-like one of those in Figure 1-and asked to judge the relationship between their meanings by picking a label from a small set: typically ENTAILMENT, NEUTRAL, and CONTRADICTION. Succeeding at NLI does not require a system to solve any difficult machine learning problems except, crucially, that of extracting effective and thorough representations for the meanings of sentences (i.e., their lexical and compositional semantics).…”

Cognitive Compositional Semantics using Continuation Dependencies

“…For example, More than two perl scripts work, can entail More than two scripts work, using a subgraph in the first argument, but Fewer than two scripts work, can entail Fewer than two perl scripts work, using a supergraph in the first argument. This consideration is similar to those observed in representations based on natural logic (MacCartney and Manning, 2009) which also uses low-level matching to perform some kinds of inference, but representations based on natural logic typically exclude other forms of inference, whereas the present model does not.…”