In the last few years, the interest of the research community in micro-blogs and social media services, such as Twitter, is growing exponentially. Yet, so far not much attention has been paid on a key characteristic of microblogs: the high level of information redundancy. The aim of this paper is to systematically approach this problem by providing an operational definition of redundancy. We ca...

The management of textual information is getting more and more attention within the case-based reasoning community. In this paper, we will address the question of how a case base can be obtained from a given textual description and how this representation scheme can be enriched by higher level concepts.

Textual entailment among sentences is an important part of applied semantic inference. In this paper we propose a novel technique to address the recognizing textual entailment challenge, which based on the distribution hypothesis that words that tend to occur in the same contexts tend to have similar meanings. Using the IDF of the overlapping words between the two propositions, we calculate the...

This paper proposes a general probabilistic setting that formalizes a probabilistic notion of textual entailment. We further describe a particular preliminary model for lexical-level entailment, based on document cooccurrence probabilities, which follows the general setting. The model was evaluated on two application independent datasets, suggesting the relevance of such probabilistic approache...

This paper describes a predominantly shallow approach to the rte-4 Challenge. We focus our attention on the non-entailing Text and Hypothesis pairs in the dataset. The system uses a Maximum Entropy framework to classify each pair of Text and Hypothesis as either yes or no, using a range of different feature sets based on an analysis of the existing non-entailing pairs in rte training data.

This paper describes the experiments developed and the results obtained in the participation of UNED in the Fourth Recognising Textual Entailment (RTE) Challenge. This year we decided to change the scope of our work with the aim of beginning to develop a system that performs a deeper analysis than the techniques used in the last editions. This participation has been the first step in the develo...

In order for a text to entail a hypothesis, the text usually must mention all of the information in the hypothesis. We use this observation as a basis for a simple system for detecting non-entailment. Unlike many previous lexically-based systems, we do not measure the degree of overlap or similarity, and we do no machine learning. This simple system performs well on the Recognizing Textual Enta...

In this paper, we describe a method for assessing student answers, modeled as a paraphrase identification problem, based on substitution by Basic English variants. Basic English paraphrases are acquired from the Simple English Wiktionary. Substitutions are applied both on reference answers and student answers in order to reduce the diversity of their vocabulary and map them to a common vocabula...

This paper presents CELI’s participation in the SemEval The Joint Student Response Analysis and 8th Recognizing Textual Entailment Challenge (Task7) and Cross-lingual Textual Entailment for Content Synchronization task (Task 8).