We promote the use of explicit medical knowledge to solve retrieval of information both visual and textual. For text, this knowledge is a set of concepts from a Meta-thesaurus, the Unified Medical Language System (UMLS). For images, this knowledge is a set of semantic features that are learned from examples using SVM within a structured learning framework. Image and text index are represented i...

We present two regression models for the prediction of pairwise preference judgments among MT hypotheses. Both models are based on feature sets that are motivated by textual entailment and incorporate lexical similarity as well as local syntactic features and specific semantic phenomena. One model predicts absolute scores; the other one direct pairwise judgments. We find that both models are co...

The Recognizing Textual Entailment System shown here is based on the use of a broad-coverage parser to extract dependency relationships; in addition, WordNet relations are used to recognize entailment at the lexical level. The work investigates whether the mapping of dependency trees from text and hypothesis give better evidence of entailment than the matching of plain text alone. While the use...

While a significant amount of research has been devoted to textual entailment, automated entailment from conversational scripts has received less attention. To address this limitation, this paper investigates the problem of conversation entailment: automated inference of hypotheses from conversation scripts. We examine two levels of semantic representations: a basic representation based on synt...

Semat (Software Engineering Method and Theory) is an initiative that allows representing common practices of existing methodologies by its core elements, which are described in terms of a language. This language has a graphical and a textual syntax. The textual syntax is described using meta-language EBNF (Extended Backus-Naur Form), which is used as context-free grammar notation to describe a ...

We develop a similarity-based textual document categorization method called the generalized instance set (GIS) algorithm. GIS integrates the advantages of linear classifiers and k-nearest neighbour algorithm by generalization of selected instances. To further enhance the performance, we propose a meta-model framework which combines the strength of different variants of GIS algorithm as well as ...

This paper presents how text summarization can be influenced by textual entailment. We show that if we use textual entailment recognition together with text summarization approach, we achieve good results for final summaries, obtaining an improvement of 6.78% with respect to the summarization approach only. We also compare the performance of this combined approach to two baselines (the one prov...

This paper addresses syntax-based paraphrasing methods for Recognizing Textual Entailment (RTE). In particular, we describe a dependency-based paraphrasing algorithm, using the DIRT data set, and its application in the context of a straightforward RTE system based on aligning dependency trees. We find a small positive effect of dependency-based paraphrasing on both the RTE3 development and test...

Work on the semantics of questions has argued that the relation between a question and its answer(s) can be cast in terms of logical entailment. In this paper, we demonstrate how computational systems designed to recognize textual entailment can be used to enhance the accuracy of current open-domain automatic question answering (Q/A) systems. In our experiments, we show that when textual entail...