Fill-in-the-blank questions are one of the main assessment devices in REAP.PT tutoring system. The problem of automatically generating the stems, i.e. the sentences that serve as basis to this type of question, has been studied mostly for English, and it remains a challenge for a language as morphologically rich as European Portuguese (EP), for which additional data scarcity problems arise. To ...

Question Generation (QG) is the task of generating reasonable questions from a text. It is a relatively new research topic and has its potential usage in intelligent tutoring systems and closed-domain question answering systems. Current approaches include template or syntax based methods. This thesis proposes a novel approach based entirely on semantics. Minimal Recursion Semantics (MRS) is a m...

When answering questions, major challenges are (a) to carefully determine the content of the answer and (b) phrase it in a proper way. In IMIX, we focus on two text-to-text generation techniques to accomplish this: content selection and sentence fusion. Using content selection, we can extend answers to an arbitrary length, providing not just a direct answer but also related information so to be...

It’s the night before his organic chemistry examination, but John isn’t ready for the test. Sure, he studied all week for the test, but he still doesn’t have a firm grasp of all the material and he knows his professors wouldn’t be happy with him if he woke them up now, at 1:30 A.M. So, he sits down at his PC and launches his browser, guiding it to the “Question Generator” homepage where he logs...

Competency Questions (CQs) are widely used in ontology development to represent the ontology requirements. Engineers can check if a CQ is satisfied manually or with software assistance. However, when a CQ is not satisfied, they need to analyze the axioms to discover what is missing. This activity may be hard and time-consuming, because of the size of the ontology and the complexity to inspect t...

Question generation tools can be used to extract a questionanswer database from text articles. We investigate how suitable this technique is for giving domain-specific knowledge to conversational characters. We tested these characters by collecting questions and answers from naive participants, running the questions through the character, and comparing the system responses to the participant an...

Automatic generation of multiple-choice questions is an emerging topic in application of natural language processing. Particularly, applying it to language testing has been proved to be useful (Sumita et al., 2005). This demo presents an novel approach of question generation using machine learning we have introduced in (Hoshino and Nakagawa, 2005). Our study aims to generate TOEIC-like 1 multip...

AS part of our long-term research into techniques for information retrieval from natural language data bases, we have developed over the past few years a natural language interface for data base retrieval [1,2]. In developing this system, we have sought general, conceptually simple, linguistically-based solutlons to problems of semantic representation and interpretation. One component of the sy...

We describe an extensible approach to generating questions for the purpose of reading comprehension assessment and practice. Our framework for question generation composes general-purpose rules to transform declarative sentences into questions, is modular in that existing NLP tools can be leveraged, and includes a statistical component for scoring questions based on features of the input, outpu...

If-then rules are the core knowledge representation technology in currently deployed expert systems. However, if we replace rules by constraints, we can greatly extend both the expressive and reasoning functionality of such systems. An open issue, however, is how best should constraint-based expert systems decide which questions to ask their users during a consultation – how can an interactive ...