Introducing Feedback in Qanary: How Users Can Interact with QA Systems
نویسندگان
چکیده
Providing a general and efficient Question Answering system over Knowledge Bases (KB) has been studied for years. Most of the works concentrated on the automatic translation of a natural language question into a formal query. However, few works address the problem on how users can interact with Question Answering systems during this translation process. We present a general mechanism that allows users to interact with Question Answering systems. It is built on top of Qanary, a framework for integrating Question Answering components. We show how the mechanism can be applied in a generalized way. In particular, we show how it can be used when the user asks ambiguous questions.
منابع مشابه
The Qanary Ecosystem: Getting New Insights by Composing Question Answering Pipelines
The field of Question Answering (QA) is very multi-disciplinary as it requires expertise from a large number of areas such as natural language processing (NLP), artificial intelligence, machine learning, information retrieval, speech recognition and semantic technologies. In the past years a large number of QA systems were proposed using approaches from different fields and focusing on particul...
متن کاملQanary - The Fast Track to Creating a Question Answering System with Linked Data Technology
Question answering (QA) systems focus on making sense out of data via an easy-to-use interface. However, these systems are very complex and integrate a lot of technology tightly. Previously presented QA systems are mostly singular and monolithic implementations. Hence, their reusability is limited. In contrast, we follow the research agenda of establishing an ecosystem for components of QA syst...
متن کاملTrill: A Reusable Front-End for QA Systems
The Semantic Web contains an enormous amount of information in the form of knowledge bases. To make this information available to end-users many question answering (QA) systems over knowledge bases were created in the last years. Their goal is to enable users to access large amounts of structured data in the Semantic Web by bridging the gap between natural language and formal query languages li...
متن کاملInteracting meaningfully with machine learning systems: Three experiments
Although machine learning is becoming commonly used in today’s software, there has been little research into how end users might interact with machine learning systems, beyond communicating simple "right/wrong" judgments. If the users themselves could work hand-in-hand with machine learning systems, the users’ understanding and trust of the system could improve and the accuracy of learning syst...
متن کاملA New Statistical Model for Evaluation Interactive Question Answering Systems Using Regression
The development of computer systems and extensive use of information technology in the everyday life of people have just made it more and more important for them to make quick access to information that has received great importance. Increasing the volume of information makes it difficult to manage or control. Thus, some instruments need to be provided to use this information. The QA system is ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2017