Towards the domain agnostic generation of natural language explanations from provenance graphs for casual users


Richardson, Darren P. and Moreau, Luc (2016) Towards the domain agnostic generation of natural language explanations from provenance graphs for casual users At 6th International Provenance & Annotation Workshop (IPAW'16), United States. 06 - 09 Jun 2016. 12 pp, pp. 95-106. (doi:10.1007/978-3-319-40593-3_8).

Download

[img] PDF dr_ipaw16.pdf - Accepted Manuscript
Available under License University of Southampton Accepted Manuscript Licence.

Download (486kB)
[img] PDF ipaw.pdf - Other
Available under License Creative Commons Attribution Share Alike.

Download (5MB)

Description/Abstract

As more systems become PROV-enabled, there will be a cor- responding increase in the need to communicate provenance data directly to users. Whilst there are a number of existing methods for doing this — formally, diagrammatically, and textually — there are currently no application-generic techniques for generating linguistic explanations of provenance. The principal reason for this is that a certain amount of linguistic information is required to transform a provenance graph — such as in PROV — into a textual explanation, and if this information is not available as an annotation, this transformation is presently not possible. In this paper, we describe how we have adapted the common ‘consensus’ architecture from the field of natural language generation to achieve this graph transformation, resulting in the novel PROVglish architecture. We then present an approach to garnering the necessary linguistic information from a PROV dataset, which involves exploiting the linguistic information informally encoded in the URIs denoting provenance resources. We finish by detailing an evaluation undertaken to assess the effectiveness of this approach to lexicalisation, demonstrating a significant improvement in terms of fluency, comprehensibility, and grammatical correctness.

Item Type: Conference or Workshop Item (Paper)
Digital Object Identifier (DOI): doi:10.1007/978-3-319-40593-3_8
Venue - Dates: 6th International Provenance & Annotation Workshop (IPAW'16), United States, 2016-06-06 - 2016-06-09
Related URLs:
Organisations: Web & Internet Science
ePrint ID: 391910
Date :
Date Event
7 March 2016Submitted
10 April 2016Accepted/In Press
4 June 2016e-pub ahead of print
Date Deposited: 19 Apr 2016 15:39
Last Modified: 17 Apr 2017 03:40
Further Information:Google Scholar
URI: http://eprints.soton.ac.uk/id/eprint/391910

Actions (login required)

View Item View Item