Learning Canonical Forms of Entailment Rules
نویسندگان
چکیده
We propose a modular approach to paraphrase and entailment-rule learning that addresses the morphosyntactic variability of lexical-syntactic templates. Using an entailment module that captures generic morpho-syntactic regularities, we transform every identified template into a canonical form. This way, statistics from different template variations are accumulated for a single template form. Additionally, morpho-syntactic redundant rules are not acquired. This scheme also yields more informative evaluation for the acquisition quality, since the bias towards rules with many frequent variations is avoided.
منابع مشابه
Learning Entailment Rules for Unary Templates
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 outpe...
متن کاملGlobal Learning of Typed Entailment Rules
Extensive knowledge bases of entailment rules between predicates are crucial for applied semantic inference. In this paper we propose an algorithm that utilizes transitivity constraints to learn a globally-optimal set of entailment rules for typed predicates. We model the task as a graph learning problem and suggest methods that scale the algorithm to larger graphs. We apply the algorithm over ...
متن کاملEfficient Global Learning of Entailment Graphs
Entailment rules between predicates are fundamental to many semantic-inference applications. Consequently, learning such rules has been an active field of research in recent years. Methods for learning entailment rules between predicates that take into account dependencies between different rules (e.g., entailment is a transitive relation) have been shown to improve rule quality, but suffer fro...
متن کاملLearning Shallow Semantic Rules for Textual Entailment
In this paper we present a novel technique for integrating lexical-semantic knowledge in systems for learning textual entailment recognition rules: the typed anchors. These describe the semantic relations between words across an entailment pair. We integrate our approach in the cross-pair similarity model. Experimental results show that our approach increases performance of cross-pair similarit...
متن کاملGlobal Learning of Textual Entailment Graphs
Two decades after the introduction of the World Wide Web, the world is experiencing an “information explosion”, that is, a rapid increase in the amount of available textual information (55). Consequently, the longstanding dream of developing systems that perform semantic inference over natural language text has become ever more pressing. Such systems are invaluable for many natural language und...
متن کامل