Natural Language Processing
 
Edit

Text Generation

1971 papers with code • 217 benchmarks • 173 datasets

Text Generation is the task of generating text with the goal of appearing indistinguishable to human-written text. This task is more formally known as "natural language generation" in the literature.

Text generation can be addressed with Markov processes or deep generative models like LSTMs. Recently, some of the most advanced methods for text generation include BART, GPT and other GAN-based approaches. Text generation systems are evaluated either through human ratings or automatic evaluation metrics like METEOR, ROUGE, and BLEU.

Further readings:

( Image credit: Adversarial Ranking for Language Generation )

Libraries

Use these libraries to find Text Generation models and implementations
huggingface/transformers
10 papers
144,268
UFAL-DSG/tgen
6 papers
206
iinemo/lm-polygraph
5 papers
267

Datasets

Subtasks

Most implemented papers

Most implemented Social Latest No code

Learning Transferable Visual Models From Natural Language Supervision

openai/CLIP • • 26 Feb 2021

State-of-the-art computer vision systems are trained to predict a fixed set of predetermined object categories.

82
Paper
Code

Show and Tell: A Neural Image Caption Generator

yashk2810/Image-Captioning • • CVPR 2015

Experiments on several datasets show the accuracy of the model and the fluency of the language it learns solely from image descriptions.

74
Paper
Code

Generating Sequences With Recurrent Neural Networks

karpathy/char-rnn • • 4 Aug 2013

This paper shows how Long Short-term Memory recurrent neural networks can be used to generate complex sequences with long-range structure, simply by predicting one data point at a time.

59
Paper
Code

BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension

huggingface/transformers • • ACL 2020

We evaluate a number of noising approaches, finding the best performance by both randomly shuffling the order of the original sentences and using a novel in-filling scheme, where spans of text are replaced with a single mask token.

47
Paper
Code

Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Models

ashwinkalyan/dbs • • 7 Oct 2016

We observe that our method consistently outperforms BS and previously proposed techniques for diverse decoding from neural sequence models.

25
Paper
Code

SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient

LantaoYu/SeqGAN • • 18 Sep 2016

As a new way of training generative models, Generative Adversarial Nets (GAN) that uses a discriminative model to guide the training of the generative model has enjoyed considerable success in generating real-valued data.

23
Paper
Code

Language Models are Unsupervised Multitask Learners

openai/gpt-2 • • Preprint 2019

Natural language processing tasks, such as question answering, machine translation, reading comprehension, and summarization, are typically approached with supervised learning on taskspecific datasets.

21
Paper
Code

BERTScore: Evaluating Text Generation with BERT

Tiiiger/bert_score • • ICLR 2020

We propose BERTScore, an automatic evaluation metric for text generation.

18
Paper
Code

BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models

salesforce/lavis • • Conference 2023

The cost of vision-and-language pre-training has become increasingly prohibitive due to end-to-end training of large-scale models.

16
Paper
Code

Prefix-Tuning: Optimizing Continuous Prompts for Generation

XiangLi1999/PrefixTuning • • ACL 2021

Fine-tuning is the de facto way to leverage large pretrained language models to perform downstream tasks.

13
Paper
Code
Contact us on: hello@paperswithcode.com . Papers With Code is a free resource with all data licensed under CC-BY-SA.
Terms Data policy Cookies policy