TransCP: A Transformer Pointer Network for Generic Entity Description Generation With Explicit Content-Planning
No Preview Available
Citations
Altmetric:
Altmetric::
Associated Records
Authors
File Licence
Editors
Date
2023-12-01
Source Title
IEEE Transactions on Knowledge and Data Engineering
Journal Title
Journal ISSN
Volume Title
Publisher
IEEE COMPUTER SOC
Melbourne Authors
Affiliation
Computing and Information Systems
Document Type
Journal Article
Subject Code
Citation
Trisedya, B. D., Qi, J., Zheng, H., Salim, F. D. & Zhang, R. (2023). TransCP: A Transformer Pointer Network for Generic Entity Description Generation With Explicit Content-Planning. IEEE Transactions on Knowledge and Data Engineering, 35 (12), pp.13070-13082. https://doi.org/10.1109/TKDE.2023.3271971.
Access Status
This item is currently not available from this repository
Access URL
Open Access URL
Open Access at PMC
Linked Resource URL
NHMRC Grant Code
ARC Grant Code
Description
Abstract
We study neural data-to-text generation to generate a sentence to describe a target entity based on its attributes. Specifically, we address two problems of the encoder-decoder framework for data-to-text generation: i) how to encode a non-linear input (e.g., a set of attributes); and ii) how to order the attributes in the generated description. Existing studies focus on the encoding problem but do not address the ordering problem, i.e., they learn the content-planning implicitly. The other approaches focus on two-stage models but overlook the encoding problem. To address the two problems at once, we propose a model named TransCP to explicitly learn content-planning and integrate them into a description generation model in an end-to-end fashion. We propose a novel Transformer-based Pointer Network with gated residual attention and importance masking to learn a content-plan. To integrate the content-plan with a description generator, we propose a tracking mechanism to trace the extent to which the content-plan is exposed in the previous decoding time-step. This helps the description generator select the attributes to be mentioned in proper order. Experimental results show that our model consistently outperforms state-of-the-art baselines by up to 2% and 3% in terms of BLEU score on two real-world datasets.