This article presents the experiments carried out at Jadavpur University as part of the participation in Semantic Textual Similarity (STS) of Task 6 @ Semantic Evaluation Exercises (SemEval-2012). Task-6 of SemEval2012 focused on semantic relations of text pair. Task-6 provides five different text pair files to compare different semantic relations and judge these relations through a similarity ...

The work presented in this paper attempts to evaluate and quantify the use of discourse relations in the context of blog summarization and compare their use to more traditional and factual texts. Specifically, we measured the usefulness of 6 discourse relations namely comparison, contingency, illustration, attribution, topic-opinion, and attributive for the task of text summarization from blogs...

This paper describes an experimental generic software development environment which provides support for both textual and diagram-matic documents, and for visualisation of additional implicit relations between and within such documents. The relevant document structures are identiied, a framework for deening these structures and their associated presentations is introduced, and the current state...

The purpose of the RefLex annotation scheme (Baumann and Riester 2012) is the two-dimensional analysis of textual or spoken corpus data with regard to referential information status (including coreference and bridging) as well as lexical information status (semantic relations). We provide some linguisticphilosophical background followed by detailed guidelines, which can be used in combination w...

This paper focuses on the improvement of the conceptual structure of FrameNet for the sake of applying this resource to knowledgeintensive NLP tasks requiring reasoning, such as question answering, information extraction etc. Ontological analysis supported by data-driven methods is used for axiomatizing, enriching and cleaning up frame relations. The impact of the achieved axiomatization is inv...

Many argumentation tools have been proposed nowadays to support the users in on-line social discussions. However, the main drawback of these tools is that they do not cope with the automatic generation of the arguments from the natural language discussions of the users. In this paper, we propose to use a technique from computational linguistics, namely textual entailment, to generate in an auto...

This paper proposes a methodology for generating specialized Japanese data sets for textual entailment, which consists of pairs decomposed into basic sentence relations. We experimented with our methodology over a number of pairs taken from the RITE-2 data set. We compared our methodology with existing studies in terms of agreement, frequencies and times, and we evaluated its validity by invest...

Having in mind the importance that lexical resources play nowadays in natural language processing (NLP), this research aims the automatic creation of a lexical ontology for Portuguese. For its purpose, patterns in textual resources will be exploited in order to acquire relations between concepts. The ontology will be evaluated and then made available for the community.