DBMSs Should Talk Back Too

TL;DR

This paper advocates for developing natural language interfaces that can translate database query results and data back into natural language to improve verification, validation, and user interaction with database systems.

Contribution

It introduces the novel concept of reverse translation from database results and data into natural language, highlighting technical challenges and research problems involved.

Findings

Identifies the need for expressive and effective natural language translation in databases.

Highlights technical challenges in achieving accurate and fast reverse translation.

Proposes research problems for data and query translation in natural language interfaces.

Abstract

Natural language user interfaces to database systems have been studied for several decades now. They have mainly focused on parsing and interpreting natural language queries to generate them in a formal database language. We envision the reverse functionality, where the system would be able to take the internal result of that translation, say in SQL form, translate it back into natural language, and show it to the initiator of the query for verification. Likewise, information extraction has received considerable attention in the past ten years or so, identifying structured information in free text so that it may then be stored appropriately and queried. Validation of the records stored with a backward translation into text would again be very powerful. Verification and validation of query and data input of a database system correspond to just one example of the many important applications that would benefit greatly from having mature techniques for translating such database constructs into free-flowing text. The problem appears to be deceivingly simple, as there are no ambiguities or other complications in interpreting internal database elements, so initially a straightforward translation appears adequate. Reality teaches us quite the opposite, however, as the resulting text should be expressive, i.e., accurate in capturing the underlying queries or data, and effective, i.e., allowing fast and unique interpretation of them. Achieving both of these qualities is very difficult and raises several technical challenges that need to be addressed. In this paper, we first expose the reader to several situations and applications that need translation into natural language, thereby, motivating the problem. We then outline, by example, the research problems that need to be solved, separately for data translations and query translations.