paper-with-me

홈 › Papers

Generating High-Quality Surface Realizations Using Data Augmentation and Factored Sequence Models

2018-05-20 · WS 2018 7 · Henry Elder, Chris Hokamp

This work presents a new state of the art in reconstruction of surface realizations from obfuscated text. We identify the lack of sufficient training data as the major obstacle to training high-performing models, and solve this issue by generating large amounts of synthetic training data. We also propose preprocessing techniques which make the structure contained in the input features more accessible to sequence models. Our models were ranked first on all evaluation metrics in the English portion of the 2018 Surface Realization shared task.

📄 PDF Abstract BibTeX arXiv:1805.07731

Code (0)

등록된 구현이 없습니다.

Tasks

Data Augmentation

Similar Papers 제목 키워드 기반

Latent-Constrained Conditional VAEs for Augmenting Large-Scale Climate Ensembles

2026-01-01 · Jacquelyn Shelton, Przemyslaw Polewski, Alexander Robel, Matthew Hoffman 외 arxiv

Large climate-model ensembles are computationally expensive; yet many downstream analyses would benefit from additional, statistically consistent realizations of spatiotemporal climate variables. We study a generative mo…

Parametrization of stochastic inputs using generative adversarial networks with application in geology

2019-04-07 · Shing Chan, Ahmed H. Elsheikh

We investigate artificial neural networks as a parametrization tool for stochastic inputs in numerical simulations. We address parametrization from the point of view of emulating the data generating process, instead of e…

Dimensionality Reductionparameter estimationUncertainty Quantification

Deep-learning-based coupled flow-geomechanics surrogate model for CO$_2$ sequestration

2021-05-04 · Meng Tang, Xin Ju, Louis J. Durlofsky

A deep-learning-based surrogate model capable of predicting flow and geomechanical responses in CO2 storage operations is presented and applied. The 3D recurrent R-U-Net model combines deep convolutional and recurrent ne…

Deep-Learned Generators of Porosity Distributions Produced During Metal Additive Manufacturing

2022-05-11 · Francis Ogoke, Kyle Johnson, Michael Glinsky, Chris Laursen 외

Laser Powder Bed Fusion has become a widely adopted method for metal Additive Manufacturing (AM) due to its ability to mass produce complex parts with increased local control. However, AM produced parts can be subject to…

Decoupling Strategy and Surface Realization for Task-oriented Dialogues

2021-09-29 · Chenchen Ye, Lizi Liao, Fuli Feng, Wei Ji 외

Task-oriented dialogue systems assist users in completing various tasks by generating appropriate responses. The key lies in effective strategy learning and surface realization, which are largely mixed together by the cu…

Reinforcement Learning (RL)Style TransferTask-Oriented Dialogue Systems