Plan-then-Generate: Controlled Data-to-Text Generation via Planning
- URL: http://arxiv.org/abs/2108.13740v1
- Date: Tue, 31 Aug 2021 10:53:32 GMT
- Title: Plan-then-Generate: Controlled Data-to-Text Generation via Planning
- Authors: Yixuan Su, David Vandyke, Sihui Wang, Yimai Fang, Nigel Collier
- Abstract summary: We propose a novel Plan-then-Generate (PlanGen) framework to improve the controllability of neural data-to-text models.
Our model is able to control both the intra-sentence and inter-sentence structure of the generated output.
- Score: 11.127156275580305
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Recent developments in neural networks have led to the advance in
data-to-text generation. However, the lack of ability of neural models to
control the structure of generated output can be limiting in certain real-world
applications. In this study, we propose a novel Plan-then-Generate (PlanGen)
framework to improve the controllability of neural data-to-text models.
Extensive experiments and analyses are conducted on two benchmark datasets,
ToTTo and WebNLG. The results show that our model is able to control both the
intra-sentence and inter-sentence structure of the generated output.
Furthermore, empirical comparisons against previous state-of-the-art methods
show that our model improves the generation quality as well as the output
diversity as judged by human and automatic evaluations.
Related papers
- CAR: Controllable Autoregressive Modeling for Visual Generation [100.33455832783416]
Controllable AutoRegressive Modeling (CAR) is a novel, plug-and-play framework that integrates conditional control into multi-scale latent variable modeling.
CAR progressively refines and captures control representations, which are injected into each autoregressive step of the pre-trained model to guide the generation process.
Our approach demonstrates excellent controllability across various types of conditions and delivers higher image quality compared to previous methods.
arXiv Detail & Related papers (2024-10-07T00:55:42Z) - Controllable Text Generation with Neurally-Decomposed Oracle [91.18959622763055]
We propose a framework to control auto-regressive generation models with NeurAlly-Decomposed Oracle (NADO)
We present a closed-form optimal solution to incorporate the token-level guidance into the base model for controllable generation.
arXiv Detail & Related papers (2022-05-27T20:17:53Z) - RSTGen: Imbuing Fine-Grained Interpretable Control into Long-FormText
Generators [26.27412809287025]
RSTGen is a framework that controls the discourse structure, semantics and topics of generated text.
We demonstrate our model's ability to control structural discourse and semantic features of generated text in open generation evaluation.
arXiv Detail & Related papers (2022-05-25T09:06:04Z) - Data-to-text Generation with Variational Sequential Planning [74.3955521225497]
We consider the task of data-to-text generation, which aims to create textual output from non-linguistic input.
We propose a neural model enhanced with a planning component responsible for organizing high-level information in a coherent and meaningful way.
We infer latent plans sequentially with a structured variational model, while interleaving the steps of planning and generation.
arXiv Detail & Related papers (2022-02-28T13:17:59Z) - Few-Shot Table-to-Text Generation with Prototype Memory [14.69889589370148]
We propose a new framework: Prototype-to-Generate (P2G), for table-to-text generation under the few-shot scenario.
The proposed framework utilizes the retrieved prototypes, which are jointly selected by an IR system and a novel prototype selector.
Experimental results on three benchmark datasets with three state-of-the-art models demonstrate that the proposed framework significantly improves the model performance.
arXiv Detail & Related papers (2021-08-27T22:16:30Z) - SDA: Improving Text Generation with Self Data Augmentation [88.24594090105899]
We propose to improve the standard maximum likelihood estimation (MLE) paradigm by incorporating a self-imitation-learning phase for automatic data augmentation.
Unlike most existing sentence-level augmentation strategies, our method is more general and could be easily adapted to any MLE-based training procedure.
arXiv Detail & Related papers (2021-01-02T01:15:57Z) - Unsupervised Paraphrasing with Pretrained Language Models [85.03373221588707]
We propose a training pipeline that enables pre-trained language models to generate high-quality paraphrases in an unsupervised setting.
Our recipe consists of task-adaptation, self-supervision, and a novel decoding algorithm named Dynamic Blocking.
We show with automatic and human evaluations that our approach achieves state-of-the-art performance on both the Quora Question Pair and the ParaNMT datasets.
arXiv Detail & Related papers (2020-10-24T11:55:28Z) - Controllable Text Generation with Focused Variation [71.07811310799664]
Focused-Variation Network (FVN) is a novel model to control language generation.
FVN learns disjoint discrete latent spaces for each attribute inside codebooks, which allows for both controllability and diversity.
We evaluate FVN on two text generation datasets with annotated content and style, and show state-of-the-art performance as assessed by automatic and human evaluations.
arXiv Detail & Related papers (2020-09-25T06:31:06Z) - Neural Data-to-Text Generation with Dynamic Content Planning [26.98332458548882]
We propose a Neural data-to-text generation model with Dynamic content Planning, named NDP for abbreviation.
The NDP can utilize the previously generated text to dynamically select the appropriate entry from the given structured data.
Empirical results show that the NDP superior performance over the state-of-the-art on ROTOWIRE dataset.
arXiv Detail & Related papers (2020-04-16T02:50:51Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.