paper-with-me

Papers

Neural Data-to-Text Generation Based on Small Datasets: Comparing the Added Value of Two Semi-Supervised Learning Approaches on Top of a Large Language Model

2022-07-14 · Chris van der Lee, Thiago castro Ferreira, Chris Emmery, Travis Wiltshire, Emiel Krahmer

This study discusses the effect of semi-supervised learning in combination with pretrained language models for data-to-text generation. It is not known whether semi-supervised learning is still helpful when a large-scale language model is also supplemented. This study aims to answer this question by comparing a data-to-text system only supplemented with a language model, to two data-to-text systems that are additionally enriched by a data augmentation or a pseudo-labeling semi-supervised learning approach. Results show that semi-supervised learning results in higher scores on diversity metrics. In terms of output quality, extending the training set of a data-to-text system with a language model using the pseudo-labeling approach did increase text quality scores, but the data augmentation approach yielded similar scores to the system without training set extension. These results indicate that semi-supervised learning approaches can bolster output quality and diversity, even when a language model is also present.

📄 PDF Abstract BibTeX arXiv:2207.06839

Code (0)

등록된 구현이 없습니다.

Tasks

Data AugmentationData-to-Text GenerationDiversityLanguage ModelingLanguage ModellingLarge Language ModelText Generation

Similar Papers 제목 키워드 기반

SOEDiff: Efficient Distillation for Small Object Editing

2024-05-15 · Yiming Wu, Qihe Pan, Zhen Zhao, Zicheng Wang 외

In this paper, we delve into a new task known as small object editing (SOE), which focuses on text-based image inpainting within a constrained, small-sized area. Despite the remarkable success have been achieved by curre…

Image InpaintingObject

Treat the system like a human student: Automatic naturalness evaluation of generated text without reference texts

2018-11-01 · WS 2018 11 · Isabel Groves, Ye Tian, Ioannis Douratsos

The current most popular method for automatic Natural Language Generation (NLG) evaluation is comparing generated text with human-written reference sentences using a metrics system, which has drawbacks around reliability…

Image CaptioningMachine Translationnlg evaluationSentence+2

The Token Tax of Epistemic Accuracy: Comparing RAG and Long-Context Architectures for Document-Grounded Generative AI Applications

2026-06-18 · Austin Hamilton, Ryan Singh, Michael Wise, Ibrahim Yousif 외 arxiv

Document-grounded assistants built on large language models are increasingly used in high-stakes, knowledge-intensive work. Their usefulness, however, may depend on how evidence is allocated before generation. We investi…

Comparing Contextual and Static Word Embeddings with Small Data

2021-09-01 · KONVENS (WS) 2021 9 · Wei Zhou, Jelke Bloem
Word Embeddings

On Accurate Evaluation of GANs for Language Generation

2018-06-13 · Stanislau Semeniuta, Aliaksei Severyn, Sylvain Gelly

Generative Adversarial Networks (GANs) are a promising approach to language generation. The latest works introducing novel GAN models for language generation use n-gram based metrics for evaluation and only report single…

DiversityLanguage ModelingLanguage ModellingText Generation