NaturalLI: Natural Logic Inference for Common Sense Reasoning

Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 534–545, October 25-29, 2014, Doha, Qatar. c⃝2014 Association for Computational Linguistics NaturalLI: Natural Logic Inference for Common Sense Reasoning Gabor Angeli Stanford University Stanford, CA 94305 angeli@cs.stanford.edu Christopher D. Manning Stanford University Stanford, CA 94305 manning@cs.stanford.edu Abstract Common-sense reasoning is important for AI applications, both in NLP and many vision and robotics tasks. We propose NaturalLI: a Natural Logic inference sys- tem for inferring common sense facts – for instance, that cats have tails or tomatoes are round – from a very large database of known facts. In addition to being able to provide strictly valid derivations, the system is also able to produce derivations which are only likely valid, accompanied by an associated confidence. We both show that our system is able to capture strict Natural Logic inferences on the Fra- CaS test suite, and demonstrate its ability to predict common sense facts with 49% recall and 91% precision. 1 Introduction We approach the task of database completion: given a database of true facts, we would like to predict whether an unseen fact is true and should belong in the database. This is intuitively cast as an inference problem from a collection of candi- date premises to the truth of the query. For exam- ple, we would like to infer that no carnivores eat animals is false given a database containing the cat ate a mouse (see Figure 1). These inferences are difficult to capture in a principled way while maintaining high recall, particularly for large scale open-domain tasks. Learned inference rules are difficult to general- ize to arbitrary relations, and standard IR methods easily miss small but semantically important lex- ical differences. Furthermore, many methods re- quire explicitly modeling either the database, the query, or both in a formal meaning representation (e.g., Freebase tuples). Although projects like the Abstract Meaning Representation (Banarescu et al., 2013) have made No carnivores eat animals? The carnivores eat animals The cat eats animals The cat ate an animal The cat ate a mouse ⊒ ≡ ⊒ ⋏ No cats eat animals No cats eat mice ⊒ . . . ⊒ . . . Figure 1: Natural Logic inference cast as search. The path to the boxed premise the cat ate a mouse disproves the query no carnivores eat animals, as it passes through the negation relation (⋏). This path is one of many candidates taken; the premise is one of many known facts in the database. The edge labels denote Natural Logic inference steps. headway in providing broad-coverage meaning representations, it remains appealing to use hu- man language as the vessel for inference. Fur- thermore, OpenIE and similar projects have been very successful at collecting databases of natural language snippets from an ever-increasing corpus of unstructured text. These factors motivate our use of Natural Logic – a proof system built on the syntax of human language – for broad coverage database completion. Prior work on Natural Logic has …

Content truncated to 500 words