Li, X., van Deemter, K. and Lin, C. orcid.org/0000-0003-3454-2468 (Submitted: 2020) A text reassembling approach to natural language generation. arXiv. (Submitted)
Abstract
Recent years have seen a number of proposals for performing Natural Language Generation (NLG) based in large part on statistical techniques. Despite having many attractive features, we argue that these existing approaches nonetheless have some important drawbacks, sometimes because the approach in question is not fully statistical (i.e., relies on a certain amount of handcrafting), sometimes because the approach in question lacks transparency. Focussing on some of the key NLG tasks (namely Content Selection, Lexical Choice, and Linguistic Realisation), we propose a novel approach, called the Text Reassembling approach to NLG (TRG), which approaches the ideal of a purely statistical approach very closely, and which is at the same time highly transparent. We evaluate the TRG approach and discuss how TRG may be extended to deal with other NLG tasks, such as Document Structuring, and Aggregation. We discuss the strengths and limitations of TRG, concluding that the method may hold particular promise for domain experts who want to build an NLG system despite having little expertise in linguistics and NLG.
Metadata
Item Type: | Article |
---|---|
Authors/Creators: |
|
Copyright, Publisher and Additional Information: | © 2020 The Author(s). For reuse permissions, please contact the Author(s). |
Dates: |
|
Institution: | The University of Sheffield |
Academic Units: | The University of Sheffield > Faculty of Engineering (Sheffield) > Department of Computer Science (Sheffield) |
Depositing User: | Symplectic Sheffield |
Date Deposited: | 09 Jul 2020 06:11 |
Last Modified: | 09 Jul 2020 06:35 |
Published Version: | https://arxiv.org/abs/2005.07988 |
Status: | Submitted |
Related URLs: | |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:163022 |