paper-with-me

Papers

Data-to-text Generation with Variational Sequential Planning

2022-02-28 · Ratish Puduppully, Yao Fu, Mirella Lapata

We consider the task of data-to-text generation, which aims to create textual output from non-linguistic input. We focus on generating long-form text, i.e., documents with multiple paragraphs, and 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. Text is generated by conditioning on previous variational decisions and previously generated text. Experiments on two data-to-text benchmarks (RotoWire and MLB) show that our model outperforms strong baselines and is sample efficient in the face of limited training data (e.g., a few hundred instances).

📄 PDF Abstract BibTeX arXiv:2202.13756

Code (1)

ratishsp/data2text-seq-plan-py 공식 구현 pytorch

Tasks

Data-to-Text GenerationText Generation

Similar Papers 제목 키워드 기반

VariBASed: Variational Bayes-Adaptive Sequential Monte-Carlo Planning for Deep Reinforcement Learning

2026-02-21 · Joery A. de Vries, Jinke He, Yaniv Oren, Pascal R. van der Vaart 외 arxiv

Optimally trading-off exploration and exploitation is the holy grail of reinforcement learning as it promises maximal data-efficiency for solving any task. Bayes-optimal agents achieve this, but obtaining the belief-stat…

Reinforcement Learning

Long and Diverse Text Generation with Planning-based Hierarchical Variational Model

2019-08-19 · IJCNLP 2019 11 · Zhihong Shao, Minlie Huang, Jiangtao Wen, Wenfei Xu 외

Existing neural methods for data-to-text generation are still struggling to produce long and diverse texts: they are insufficient to model input data dynamically during generation, to capture inter-sentence coherence, or…

Data-to-Text GenerationDiversitySentenceText Generation

Adaptive Path-Integral Autoencoder: Representation Learning and Planning for Dynamical Systems

2018-07-05 · Jung-Su Ha, Young-Jin Park, Hyeok-Joo Chae, Soon-Seo Park 외

We present a representation learning algorithm that learns a low-dimensional latent dynamical system from high-dimensional \textit{sequential} raw data, e.g., video. The framework builds upon recent advances in amortized…

Representation LearningVariational Inference

Deep Human-guided Conditional Variational Generative Modeling for Automated Urban Planning

2021-10-12 · Dongjie Wang, Kunpeng Liu, Pauline Johnson, Leilei Sun 외

Urban planning designs land-use configurations and can benefit building livable, sustainable, safe communities. Inspired by image generation, deep urban planning aims to leverage deep learning to generate land-use config…

DecoderImage Generation

Adaptive Path-Integral Autoencoders: Representation Learning and Planning for Dynamical Systems

2018-12-01 · NeurIPS 2018 12 · Jung-Su Ha, Young-Jin Park, Hyeok-Joo Chae, Soon-Seo Park 외

We present a representation learning algorithm that learns a low-dimensional latent dynamical system from high-dimensional sequential raw data, e.g., video. The framework builds upon recent advances in amortized inferenc…

Representation LearningVariational Inference