A Modified, Template-Based Approach to Question-Answering from Knowledge Bases
نویسندگان
چکیده
As part of a larger project, one of our goals is to enable users, not trained in AI, to be able to pose questions to an inference-capable knowledge base (KB), and receive acceptable answers. In particular, we wish the system to support answering a wide variety of questions, including longer questions which may include scenario descriptions, without requiring users to formulate their queries in predicate logic directly. In this paper, we present the approach we have developed to deal with this problem, based on the creation of a catalog of domain-independent question types and the extension of question template methods with graphical tools. We also report on the results of an extensive evaluation of this work conducted in Summer 2001.
منابع مشابه
KBQA: An Online Template Based Question Answering System over Freebase
Question answering (QA) has become a popular way for humans to access billion-scale knowledge bases. QA systems over knowledge bases produce accurate and concise answers. The key of QA over knowledge bases is to map the question to a certain substructure in the knowledge base. To do this, KBQA (Question Answering over Knowledge Bases) uses a new kind of question representation: templates, learn...
متن کاملدستهبندی پرسشها با استفاده از ترکیب دستهبندها
Question answering systems are produced and developed to provide exact answers to the question posted in natural language. One of the most important parts of question answering systems is question classification. The purpose of question classification is predicting the kind of answer needed for the question in natural language. The literature works can be categorized as rule-based and learning...
متن کاملA Chinese Intelligent Question Answering System Based on Domain Ontology and Sentence Templates
With the development of network technology, distance education is becoming increasingly important. Intelligent question answering system is an important part of remote learning system. Currently, there have been a lot of mature English question answering systems. Owing to the Chinese natural language complexity and processing technical limitations, there is still no mature Chinese QA system exp...
متن کاملExtracting Template for Knowledge-based Question- Answering Using Conditional Random Fields
In this paper, we present an information extraction system that extracts template elements for a question-answering (QA) system in the domain of encyclopedia. We use Conditional Random Fields to extract templates from the texts of an encyclopedia. Using the proposed approach, we could achieve a 74.89% precision and a 55.77% F1 in the template extraction. In the question classification, we could...
متن کاملRecherche d'information précise dans des sources d'information structurées et non structurées : défis, approches et hybridation
This paper provides a synthesis of text-based Question Answering (QA) approaches, with emphasis on models exploiting structured representations of texts, and recent QA approaches for knowledge bases. Our goal is to show the common issues, and to identify what can be a common approach, using both the relations from textual documents and the triplets from knowledge bases. We present a few works u...
متن کامل