ROUGE is one of the first and most widely used evaluation metrics for text summarization. However, its assessment merely relies on surface similarities between peer and model summaries. Consequently, ROUGE is unable to fairly evaluate abstractive summaries including lexical variations and paraphrasing. Exploring the effectiveness of lexical resource-based models to address this issue, we adopt ...

We describe results of a study of perceptually based predictions of upcoming prosodic breaks in spontaneous Swedish speech materials by native speakers of Swedish and of standard American English. The question addressed here is the extent to which listeners are able, on the basis of acoustic and prosodic features, to predict the occurrence of upcoming boundaries, and if so, whether they are abl...

The research described here is part of a larger project with the objective of determining if a writer believes a proposition to be true or false. This task requires a deep understanding of a proposition’s semantic context, which is far beyond NLP’s state of the art. In light of this difficulty, this paper presents a shallow semantic framework that addresses the sub-problem of finding a proposit...

Review quality is determined by identifying the relevance of a review to a submission (the article or paper the review was written for). We identify relevance in terms of the semantic and syntactic similarities between two texts. We use a word order graph, whose vertices, edges and double edges help determine structure-based match across texts. We use WordNet to determine semantic relatedness. ...

In this paper we consider the problem of identifying and classifying discourse coherence relations. We report initial results over the recently released Discourse GraphBank (Wolf and Gibson, 2005). Our approach considers, and determines the contributions of, a variety of syntactic and lexico-semantic features. We achieve 81% accuracy on the task of discourse relation type classification and 70%...

We present a system for taxonomy construction that reached the first place in all subtasks of the SemEval 2016 challenge on Taxonomy Extraction Evaluation. Our simple yet effective approach harvests hypernyms with substring inclusion and Hearst-style lexicosyntactic patterns from domain-specific texts obtained via language model based focused crawling. Extracted taxonomies are evaluated on Engl...

All systems of automatic text processing are explicitly or implicitly based on two general linguistic ~ssumptlons: the assumption o~ grammatioallty of the texts processed, and the assumption of their meaningfulness. These assumptions, however, cannot be considered as absolute laws: It is not unoommon that a text, thongh acceptable to most speakers of the corresponding language, still contains s...

This paper describes the process of creation and review of a new lexico-semantic resource for the classical studies: AncientGreekWordNet. The candidate sets of synonyms (synsets) are extracted from Greek-English dictionaries, on the assumption that Greek words translated by the same English word or phrase have a high probability of being synonyms or at least semantically closely related. The pr...

Résumé. Depuis 2001, les conférences EGC ont rassemblé 1 782 chercheurs autour de l’extraction et la gestion de connaissances. En 2016, l’association EGC réfléchit à son histoire et se projette en lançant un défi à sa communauté. Que peut-on révéler sur la communauté EGC via des approches développées en EGC ? Notre étude lexico-scientométrique apporte un éclairage sur les thématiques du congrès...