The second multilingual surface realisation shared task (SR'19): Overview and evaluation results
We report results from the SR'19 Shared Task, the second edition of a multilingual surface
realisation task organised as part of the EMNLP'19 Workshop on Multilingual Surface …
realisation task organised as part of the EMNLP'19 Workshop on Multilingual Surface …
Neural data-to-text generation with LM-based text augmentation
For many new application domains for data-to-text generation, the main obstacle in training
neural models consists of a lack of training data. While usually large numbers of instances …
neural models consists of a lack of training data. While usually large numbers of instances …
Structural information preserving for graph-to-text generation
The task of graph-to-text generation aims at producing sentences that preserve the meaning
of input graphs. As a crucial defect, the current state-of-the-art models may mess up or even …
of input graphs. As a crucial defect, the current state-of-the-art models may mess up or even …
Does the order of training samples matter? improving neural data-to-text generation with curriculum learning
Recent advancements in data-to-text generation largely take on the form of neural end-to-
end systems. Efforts have been dedicated to improving text generation systems by changing …
end systems. Efforts have been dedicated to improving text generation systems by changing …
Jointly improving language understanding and generation with quality-weighted weak supervision of automatic labeling
Neural natural language generation (NLG) and understanding (NLU) models are data-
hungry and require massive amounts of annotated data to be competitive. Recent …
hungry and require massive amounts of annotated data to be competitive. Recent …
Dart: A lightweight quality-suggestive data-to-text annotation tool
We present a lightweight annotation tool, the Data AnnotatoR Tool (DART), for the general
task of labeling structured data with textual descriptions. The tool is implemented as an …
task of labeling structured data with textual descriptions. The tool is implemented as an …
Unsupervised pidgin text generation by pivoting english data and self-training
West African Pidgin English is a language that is significantly spoken in West Africa,
consisting of at least 75 million speakers. Nevertheless, proper machine translation systems …
consisting of at least 75 million speakers. Nevertheless, proper machine translation systems …
Diverse and relevant visual storytelling with scene graph embeddings
A problem in automatically generated stories for image sequences is that they use overly
generic vocabulary and phrase structure and fail to match the distributional characteristics of …
generic vocabulary and phrase structure and fail to match the distributional characteristics of …
Deep latent-variable models for text generation
X Shen - arXiv preprint arXiv:2203.02055, 2022 - arxiv.org
Text generation aims to produce human-like natural language output for down-stream tasks.
It covers a wide range of applications like machine translation, document summarization …
It covers a wide range of applications like machine translation, document summarization …
Safe handover in mixed-initiative control for cyber-physical systems
For mixed-initiative control between cyber-physical systems (CPS) and its users, it is still an
open question how machines can safely hand over control to humans. In this work, we …
open question how machines can safely hand over control to humans. In this work, we …