Natural Language Question Answering and Analytics for Diverse and Interlinked Datasets

Song, Dezhao; Schilder, Frank; Smiley, Charese; Brew, Chris

doi:10.3115/v1/n15-3021

“…NL Interfaces Multiple lines of work (e.g. [52,7,55,76,75,3,65]) have proposed NL interfaces for the formulation of database queries, and additional works [32] have focused on presenting the answers in NL, typically basing their translation on the schema of the output relation. Among these, works such as [7,55] also harness the dependency tree in order to make the translation form NL to SQL by employing mappings from the NL query to formal terms.…”

Section: Summarization Of Database Contentmentioning

confidence: 99%

Explaining Natural Language query results

Deutch

¹

,

Frost

²

,

Gilad

³

2019

View full text Add to dashboard Cite

Multiple lines of research have developed Natural Language (NL) interfaces for formulating database queries. We build upon this work, but focus on presenting a highly detailed form of the answers in NL. The answers that we present are importantly based on the provenance of tuples in the query result, detailing not only the results but also their explanations. We develop a novel method for transforming provenance information to NL, by leveraging the original NL query structure. Furthermore, since provenance information is typically large and complex, we present two solutions for its effective presentation as NL text: one that is based on provenance factorization, with novel desiderata relevant to the NL case, and one that is based on summarization. We have implemented our solution in an end-to-end system supporting questions, answers and provenance, all expressed in NL. Our experiments, including a user study, indicate the quality of our solution and its scalability.

show abstract

“…Multiple lines of work (e.g. [34,4,35,48,43,47,1]) have proposed NL interfaces to formulate database queries, and additional works [20] have focused on presenting the answers in NL, typically basing their translation on the schema of the output relation. Among these, works such as [4,35] also harness the dependency tree in order to make the translation form NL to SQL by employing mappings from the NL query to formal terms.…”

Section: Related Workmentioning

confidence: 99%

Provenance for natural language queries

Deutch

¹

,

Frost

²

,

Gilad

³

2017

View full text Add to dashboard Cite

Multiple lines of research have developed Natural Language (NL) interfaces for formulating database queries. We build upon this work, but focus on presenting a highly detailed form of the answers in NL. The answers that we present are importantly based on the provenance of tuples in the query result, detailing not only the results but also their explanations. We develop a novel method for transforming provenance information to NL, by leveraging the original NL query structure. Furthermore, since provenance information is typically large and complex, we present two solutions for its effective presentation as NL text: one that is based on provenance factorization, with novel desiderata relevant to the NL case, and one that is based on summarization. We have implemented our solution in an end-to-end system supporting questions, answers and provenance, all expressed in NL. Our experiments, including a user study, indicate the quality of our solution and its scalability.

show abstract

TR Discover: A Natural Language Interface for Querying and Analyzing Interlinked Datasets

Song

¹

,

Schilder

²

,

Smiley

³

et al. 2015

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Currently, the dominant technology for providing nontechnical users with access to Linked Data is keyword-based search. This is problematic because keywords are often inadequate as a means for expressing user intent. In addition, while a structured query language can provide convenient access to the information needed by advanced analytics, unstructured keyword-based search cannot meet this extremely common need. This makes it harder than necessary for non-technical users to generate analytics. We address these difficulties by developing a natural language-based system that allows non-technical users to create wellformed questions. Our system, called TR Discover, maps from a fragment of English into an intermediate First Order Logic representation, which is in turn mapped into SPARQL or SQL. The mapping from natural language to logic makes crucial use of a feature-based grammar with full formal semantics. The fragment of English covered by the natural language grammar is domain specific and tuned to the kinds of questions that the system can handle. Because users will not necessarily know what the coverage of the system is, TR Discover offers a novel auto-suggest mechanism that can help users to construct well-formed and useful natural language questions. TR Discover was developed for future use with Thomson Reuters Cortellis, which is an existing product built on top of a linked data system targeting the pharmaceutical domain. Currently, users access it via a keyword-based query interface. We report results and performance measures for TR Discover on Cortellis, and in addition, to demonstrate the portability of the system, on the QALD-4 dataset, which is associated with a public shared task. We show that the system is usable and portable, and report on the relative performance of queries using SQL and SPARQL back ends.

show abstract

Natural Language Question Answering and Analytics for Diverse and Interlinked Datasets

Cited by 7 publications

References 19 publications

Explaining Natural Language query results

Explaining Natural Language query results

Provenance for natural language queries

TR Discover: A Natural Language Interface for Querying and Analyzing Interlinked Datasets

Contact Info

Product

Resources

About