This paper presents different ways at different steps of question answering process to improve question answer match. First we discuss about the role and the importance of question categorization to guide the pairing. In order to process linguistic criteria, we describe a question pattern based categorization. Then we propose a statistical method and a linguistic method to enhance the pairing p...

1 Presentation I present in this paper the related work to my PhD thesis. It deals with an explanation approach for the generation of extended versions of text. The explanation is considered in the sense that an expansion is intended to make what is evoked into the text version understood. In order to give an account of this aspect, we resort to the notion of text questionnability deened by Vir...

a new edition was brought out at every decade. This proves its popularity among the students and health workers for whom it is meant. This is the fifth edition of the book published by Dr. Wilson with the assistance of Mr. Fisher. In this new edition the contents have been rearranged by adding an indexed list of statutes and statutory instruments, and the readability has been increased by multi...

This short position paper attempts to place current debates about the eecacy and morality of \intel-ligent agents" into a larger historical context that includes the work of Kant, Babbage, and Minsky, among others, and that emphasizes the cyclic nature of such debates. We also try to add some social and ethical reenements to the debate.

We approach cross-lingual question answering by using a mono-lingual QA system for the source language and by translating resulting answers into the target language. As far as we are aware, this is the first cross-lingual QA system in the history of CLEF that uses this method—all other cross-lingual QA systems known to us use translation of the question or query instead. We demonstrate the feas...

In [12], Duchêne and Rigo introduced the notion of invariance for take-away games on heaps. Roughly speaking, these are games whose rulesets do not depend on the position. Given a sequence S of positive tuples of integers, the question of whether there exists an invariant game having S as set of P-positions is relevant. In particular, it was recently proved by Larsson et al. [23] that if S is a...

A significant goal of natural language processing (NLP) is to devise a system capable of machine understanding of text. A typical system can be tested on its ability to answer questions based on a given context document. One appropriate dataset for such a system is the Stanford Question Answering Dataset (SQuAD), a crowdsourced dataset of over 100k (question, context, answer) triplets. In this ...

The element of the urinary tract that remains to be examined is the urethra. At fi rst, it was assessed with the use of a convex transducer via the transperineal access (fi g. 1). The registered image indicates a pathology in the region of the urethra, but it is insuffi cient to establish a defi nite diagnosis. Therefore, a linear high-frequency probe was placed at the same site (fi g. 2) which...

We tackle the problem of answer type prediction, applying a transition-based neural network parser to understand the syntactic structure of a query and infer the focus word or phrase that contains the correct type. To achive this, we first come up with a framework to combine a dataset of labeled question-answer pairs and a type inventory into a dataset to learn types. Second, we fit a sigmoid p...

In open domain question-answering systems, numerous questions wait for answers of an explicit type. For example, the question “Which president succeeded Jacques Chirac?” requires an instance of president as answer. The method we present in this article aims at verifying that an answer given by a system corresponds to the given type. This verification is done by combining criteria provided by di...