Natural Language Processing
 
Edit

Text Generation

1503 papers with code • 21 benchmarks • 115 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
125,478
UFAL-DSG/tgen
6 papers
204

Datasets

Subtasks

Most implemented papers

Most implemented Social Latest No code

A Syntactic Neural Model for General-Purpose Code Generation

pcyin/NL2code • ACL 2017

We consider the problem of parsing natural language descriptions into source code written in a general-purpose programming language like Python.

6
Paper
Code

Geometric GAN

open-mmlab/mmgeneration • • 8 May 2017

Generative Adversarial Nets (GANs) represent an important milestone for effective generative models, which has inspired numerous variants seemingly different from each other.

6
Paper
Code

Long Text Generation via Adversarial Training with Leaked Information

CR-Gjx/LeakGAN • • 24 Sep 2017

Automatically generating coherent and semantically meaningful text has many applications in machine translation, dialogue systems, image captioning, etc.

6
Paper
Code

fairseq: A Fast, Extensible Toolkit for Sequence Modeling

pytorch/fairseq • • NAACL 2019

fairseq is an open-source sequence modeling toolkit that allows researchers and developers to train custom models for translation, summarization, language modeling, and other text generation tasks.

6
Paper
Code

Training language GANs from Scratch

deepmind/deepmind-research • • NeurIPS 2019

Generative Adversarial Networks (GANs) enjoy great success at image generation, but have proven difficult to train in the domain of natural language.

6
Paper
Code

GLTR: Statistical Detection and Visualization of Generated Text

HendrikStrobelt/detecting-fake-text • ACL 2019

The rapid improvement of language models has raised the specter of abuse of text generation systems.

6
Paper
Code

Neural Text Generation with Unlikelihood Training

facebookresearch/unlikelihood_training • • ICLR 2020

Neural text generation is a key tool in natural language applications, but it is well known there are major problems at its core.

5
Paper
Code

Encode, Tag, Realize: High-Precision Text Editing

google-research/lasertagger • • IJCNLP 2019

We propose LaserTagger - a sequence tagging approach that casts text generation as a text editing task.

5
Paper
Code

FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation

shmsw25/factscore • • 23 May 2023

Evaluating the factuality of long-form text generated by large language models (LMs) is non-trivial because (1) generations often contain a mixture of supported and unsupported pieces of information, making binary judgments of quality inadequate, and (2) human evaluation is time-consuming and costly.

5
Paper
Code

Multiresolution Recurrent Neural Networks: An Application to Dialogue Response Generation

julianser/Ubuntu-Multiresolution-Tools • 2 Jun 2016

We introduce the multiresolution recurrent neural network, which extends the sequence-to-sequence framework to model natural language generation as two parallel discrete stochastic processes: a sequence of high-level coarse tokens, and a sequence of natural language tokens.

4
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