Predicting Correlations Between Lexical Alignments and Semantic Inferences
نویسندگان
چکیده
While there is a strong intuition that word alignments (e.g. synonymy, hyperonymy) play a relevant role in recognizing textto-text semantic inferences (e.g. textual entailment, semantic similarity), this intuition is often not reflected in the system performances and there is a general need of a deeper comprehension of the role of lexical resources. This paper provides an empirical analysis of the dependencies between data-sets, lexical resources and algorithms that are commonly used in text-to-text inference tasks. We define a resource impact index, based on lexical alignments between pairs of texts, and show that such index is significantly correlated with the performance of different textual entailment algorithms. The result is an operational, algorithm-independent, procedure for predicting the performance of a class of available RTE algorithms.
منابع مشابه
Adding Context to Semantic Data-Driven Paraphrasing
Recognizing lexical inferences between pairs of terms is a common task in NLP applications, which should typically be performed within a given context. Such context-sensitive inferences have to consider both term meaning in context as well as the fine-grained relation holding between the terms. Hence, to develop suitable lexical inference methods, we need datasets that are annotated with fine-g...
متن کاملDetecting Cross-lingual Semantic Similarity Using Parallel PropBanks
This paper suggests a method for detecting cross-lingual semantic similarity using parallel PropBanks. We begin by improving word alignments for verb predicates generated by GIZA++ by using information available in parallel PropBanks. We applied the Kuhn-Munkres method to measure predicateargument matching and improved verb predicate alignments by an F-score of 12.6%. Using the enhanced word al...
متن کاملThe Effect of Semantic Transfer on Iranian EFL Learners’ Lexical Representation and Processing
متن کامل
Semantic Inference at the Lexical-Syntactic Level
Semantic inference is an important component in many natural language understanding applications. Classical approaches to semantic inference rely on complex logical representations. However, practical applications usually adopt shallower lexical or lexical-syntactic representations, but lack a principled inference framework. We propose a generic semantic inference framework that operates direct...
متن کاملMatching Terminological Heterogeneous Ontologies by Exploiting Partial Alignments
Matching ontologies which utilize significantly heterogeneous terminologies is a challenging task for existing matching techniques. These techniques typically exploit lexical resources in order to enrich the ontologies with additional terminology such that more terminological matches can be found. However, they are limited by the availability of an appropriate lexical resource for each matching...
متن کامل