This paper presents an approach to creating intelligent conversational agents that are capable of returning appropriate responses to natural language input. Our approach consists of using a supervised learning algorithm in combination with different NLP algorithms in training the system to identify paraphrases of the user’s question stored in a database. When tested on a data set consisting of ...

At the NTCIR5 CLQA task, we participated in the Chinese-Chinese (CC) and English-Chinese (EC) QA subtasks. Due to some programming errors in our EC QA system, we will focus on the evaluation of our CC QA system in this paper. We propose a new method to improve answer ranking using the cohesion between answer and keywords. Our experimental results show the effectiveness of this new method. Besid...

In this work, questions are tasks posed to students to help them understand a subject, or to help educators assess their level of competency in it. Automated question generation is important today as content providers in education try to scale their efforts. In particular, MOOCs need a continuous supply of new questions in order to offer educational content to thousands of students, and to prov...

Stack Overflow and MedHelp are examples of domainspecific community-based question answering (CQA) systems. Different from CQA systems for general topics (e.g., Yahoo! Answers, Baidu Knows), questions and answers in domain-specific CQA systems are mostly in the same topical domain, enabling more comprehensive interaction between users on fine-grained topics. In such systems, users are more like...

We show that a neural approach to the task of non-factoid answer reranking can benefit from the inclusion of tried-and-tested handcrafted features. We present a novel neural network architecture based on a combination of recurrent neural networks that are used to encode questions and answers, and a multilayer perceptron. We show how this approach can be combined with additional features, in par...

The goal of this paper is to derive a measure of utility for questions and answers from a game theoretic model of communication. We apply this measure to account for a number of judgements about the appropriateness of partial and mention–some answers, e.g. that a partial answers to a question can be as appropriate as a strongly exhaustive answer. Under the assumption that interlocutors are Baye...

Taking the lead from orthodox quantum theory, I will introduce a handy generalization of the Boolean approach to propositions and questions: the ortho-algebraic framework. I will demonstrate that this formalism relates to a formal theory of questions (or ‘observables’ in the physicist’s jargon). This theory allows to formulate conditioned questions such as “if electron 1 has spin ↑ what is the ...

This paper presents a chatterbot that answers or asks questions in Portuguese about a basic education text. From an input text composed of simple sentences, the questions and answers are generated in the chatterbot knowledge base. For this purpose, a morphosyntactic analysis is made and the semantic roles of each word are obtained. Seven semantic roles are treated, from which is defined what pr...

Purpose: This study examines to which degree General Finnish Thesaurus (GFT) and FinMeSH cover various semantic expressions of medical concepts in patients' questions and physicians' answers concerning cardiovascular diseases. The former represent lay persons’ information needs. Methodology: 50 question answer pairs were collected in a medical Web site. Concepts and their expressions (terms) wi...

Community Question Answering (CQA) portals provide rich sources of information on a variety of topics. However, the authenticity and quality of questions and answers (Q&As) has proven hard to control. In a troubling direction, the widespread growth of crowdsourcing websites has created a large-scale, potentially difficult-to-detect workforce to manipulate malicious contents in CQA. The crowd wo...