Answering open-ended questions is an essential capability for any intelligent agent. One of the most interesting recent open-ended question answering challenges is Visual Question Answering (VQA) which attempts to evaluate a system’s visual understanding through its answers to natural language questions about images. There exist many approaches to VQA, the majority of which do not exhibit deepe...

Our QA system is constructed using methods of classical IR, enhanced with simple heuristics. It does not have natural language understanding capabilities, but employs simple pattern matching and statistics. We view QA as a three-step process: 1) retrieving a set of documents that are highly related to the topic of the question; 2) weighing sentences in this document set that are most likely to ...

Natural Semantics is a logical formalism used to specify semantic aspects of a language by sets of logical rules (called a Typol program) where a query is proved using Prolog. In a previous paper, we have shown how to replace, under certain hypotheses, the Prolog engine by a functional evaluator; this is possible because uniication is no longer required and can be replaced by pattern matching. ...

Most definitional question answering (QA) systems integrate statistical ranking using Web and WordNet as external resources and pattern matching to retrieve relevant sentences for further processing. We examine the impact of using these two common resources in answering definition questions by varying the use of WordNet and two types of Web resources in statistical ranking, and definition patte...

This paper proposes a method for extracting Daily Changing Words (DCWs), words that indicate which questions are realtime dependent. Our approach is based on two types of template matching using time and named entity slots from large size corpora and adding simple filtering methods from news corpora. Extracted DCWs are utilized for detecting and sorting real-time dependent questions. Experiment...

This study addresses the problem of 3D shape retrieval. While this problem is interesting and emerging as the size of 3D object databases grows rapidly, the main two issues the community has to focus on are: computational efficiency of 3D object retrieval and the quality of retrieval results. In this study we deal with the two considerations, especially the first one namely computational effici...

The paper presents an approach to answer extraction for a Question Answering Dialogue System (QADS), which is a part of an interactive quiz game. The information that forms the content of this game is concerned with biographical facts of famous people’s life. The facts are extracted from Wikipedia pages by means of semantic relations, whose fillers are identified by trained sequence classifiers...

We revisit the question of priors that achieve approximate matching of Bayesian and frequentist predictive probabilities. Such priors may be thought of as providing frequentist calibration of Bayesian prediction or simply as devices for producing frequentist prediction regions. Here we analyse the O(n) term in the expansion of the coverage probability of a Bayesian prediction region, as derived...

Matching Dependencies (MDs) are a relatively recent pro-posal for declarative entity resolution. They are rules thatspecify, on the basis of similarities satisfied by values in a database, what values should be considered duplicates, and have to be matched. On the basis of a chase-like procedurefor MD enforcement, we can obtain clean (duplicate-free)instances; actually possibly ...