Abstract
The discordance between expressions interpretable by a natural language interface (NLI) system and those answerable by a knowledge base is a critical problem in the field of NLIs. In order to solve this discordance problem, this paper proposes a method to translate natural language questions into formal queries that can be generated from a graph-based knowledge base. The proposed method considers a subgraph of a knowledge base as a formal query. Thus, all formal queries corresponding to a concept or a predicate in the knowledge base can be generated prior to query time and all possible natural language expressions corresponding to each formal query can also be collected in advance. A natural language expression has a one-to-one mapping with a formal query. Hence, a natural language question is translated into a formal query by matching the question with the most appropriate natural language expression. If the confidence of this matching is not sufficiently high the proposed method rejects the question and does not answer it. Multipredicate queries are processed by regarding them as a set of collected expressions. The experimental results show that the proposed method thoroughly handles answerable questions from the knowledge base and rejects unanswerable ones effectively.
Highlights
The studies in the field of natural language interfaces (NLIs) have attempted to match natural language questions with formal queries for easy access of information stored in a knowledge base
The experiments in this study showed that an iterative customization of rules by the graphical user interface (GUI) steadily improves the performance of NLI
The discordance between the questions interpretable by the interface and those answerable by the knowledge base is a major problem in the field of NLIs
Summary
The studies in the field of natural language interfaces (NLIs) have attempted to match natural language questions with formal queries for easy access of information stored in a knowledge base. A possible question that can be matched with this formal query is as follows: “Which rivers run through the state with the lowest elevation in the USA?” it is not easy for casual users to write such a question in a formal query language. Various types of query interfaces such as menu-guided interfaces [2], graphical query composers [3], and NLIs [4] have been proposed to improve the accessibility to knowledge bases Among these query interfaces, NLIs allow more precise query expressions to be written with relative ease because users are more familiar with wordbased query interfaces than with other graphical- or menudriven interfaces. NLIs that translate natural language questions into their corresponding formal language queries have been studied extensively [5]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
