Abstract—Keyword Search is known as a user-friendly alternative for structured languages to retrieve information from graph-structured data. Efficient retrieving of relevant answers to a keyword query and effective ranking of these answers according to their relevance are two main challenges in the keyword search over graph-structured data. In this paper, a novel scoring function is proposed, w...

Question-answering chatbots have tremendous potential to complement humans in various fields. They are implemented using either rule-based or machine learning-based systems. Unlike the former, more scalable. Sequence-to-sequence (Seq2Seq) learning is one of most popular approaches and has shown remarkable progress since its introduction 2014. However, based on Seq2Seq show a weakness that it te...

Identifying relevant results is a key task in XML keyword search (XKS). Although many approaches have been proposed for this task, effectively identifying results for XKS is still an open problem. In this paper, we propose a novel approach for identifying relevant results for XKS by adopting the concept of Mutual Information and skyline semantics. Specifically, we introduce a measurement to eff...

We have investigated the potential use of question answering systems and participated in the Question Answering Challenge (QAC) of National institute of informatics Test Collection for Information Retrieval systems (NTCIR). In this paper, we describe our question answering system, the preliminary results of our experiments to the contest and some possible improvement to question answering systems.

Question answering systems try to give precise answers to a user's question posed in natural language. It is of utmost importance that the answers returned are relevant to the user's question. For clinical QA, the trustworthiness of answers is another important issue. Limiting the document collection to certified websites helps to improve the trustworthiness of answers. On the other hand, limit...

In this paper, we propose a new method for keyword search over large graph-structured data to find a set of answers which are not only relevant to the query but also reduced and duplication-free. We define an effective answer structure and a relevance measure for the candidate answers to a keyword query on graph data. We suggest an efficient indexing scheme on relevant and useful paths from nod...