Text Generation

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.

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 1051–1075 of 5335 papers

Title	Date	Tasks	Status	Hype
CTRL: A Conditional Transformer Language Model for Controllable Generation	Sep 11, 2019	Language ModelingLanguage Modelling	CodeCode Available	1
Select and Attend: Towards Controllable Content Selection in Text Generation	Sep 10, 2019	DecoderHeadline Generation	CodeCode Available	1
Out-of-domain Detection for Natural Language Understanding in Dialog Systems	Sep 9, 2019	Generative Adversarial NetworkNatural Language Understanding	CodeCode Available	1
The Woman Worked as a Babysitter: On Biases in Language Generation	Sep 3, 2019	Language ModelingLanguage Modelling	CodeCode Available	1
Image Captioning with Sparse Recurrent Neural Network	Aug 28, 2019	Image CaptioningText Generation	CodeCode Available	1
Transforming Delete, Retrieve, Generate Approach for Controlled Text Style Transfer	Aug 25, 2019	SentenceStyle Transfer	CodeCode Available	1
Neural Text Generation with Unlikelihood Training	Aug 12, 2019	BlockingText Generation	CodeCode Available	1
Hello, It's GPT-2 -- How Can I Help You? Towards the Use of Pretrained Language Models for Task-Oriented Dialogue Systems	Jul 12, 2019	Decision MakingLanguage Modeling	CodeCode Available	1
Dual Supervised Learning for Natural Language Understanding and Generation	May 15, 2019	Natural Language UnderstandingText Generation	CodeCode Available	1
BERTScore: Evaluating Text Generation with BERT	Apr 21, 2019	Image CaptioningMachine Translation	CodeCode Available	1
Jointly Measuring Diversity and Quality in Text Generation Models	Apr 8, 2019	DiversitySentence	CodeCode Available	1
Text Generation from Knowledge Graphs with Graph Transformers	Apr 4, 2019	DecoderDialogue Generation	CodeCode Available	1
fairseq: A Fast, Extensible Toolkit for Sequence Modeling	Apr 1, 2019	Language ModelingLanguage Modelling	CodeCode Available	1
What makes a good conversation? How controllable attributes affect human judgments	Feb 22, 2019	SpecificityText Generation	CodeCode Available	1
Language Models are Unsupervised Multitask Learners	Feb 14, 2019	Common Sense ReasoningCoreference Resolution	CodeCode Available	1
Generating Market Comments Referring to External Resources	Nov 1, 2018	Text Generation	CodeCode Available	1
Deep Graph Convolutional Encoders for Structured Data to Text Generation	Oct 23, 2018	Data-to-Text GenerationGraph-to-Sequence	CodeCode Available	1
Paragraph-level Neural Question Generation with Maxout Pointer and Gated Self-attention Networks	Oct 1, 2018	Question AnsweringQuestion Generation	CodeCode Available	1
Learning to Generate Move-by-Move Commentary for Chess Games from Large-Scale Social Forum Data	Jul 1, 2018	Game of ChessText Generation	CodeCode Available	1
Toward Diverse Text Generation with Inverse Reinforcement Learning	Apr 30, 2018	reinforcement-learningReinforcement Learning	CodeCode Available	1
Texygen: A Benchmarking Platform for Text Generation Models	Feb 6, 2018	BenchmarkingDiversity	CodeCode Available	1
Convolutional Image Captioning	Nov 24, 2017	Image CaptioningText Generation	CodeCode Available	1
Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Models	Oct 7, 2016	DiversityImage Captioning	CodeCode Available	1
Modeling Context in Referring Expressions	Jul 31, 2016	Referring ExpressionReferring expression generation	CodeCode Available	1
Latent Predictor Networks for Code Generation	Mar 22, 2016	Card GamesCode Generation	CodeCode Available	1

Show:10 25 50

← PrevPage 43 of 214Next →

All datasets DART COCO Captions EMNLP2017 WMT ReDial CommonGen ROCStories Chinese Poems Czech restaurant information OpenWebText SciQ Yahoo Questions ADGEN

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	T5B Baseline	BLEU	48.74	—	Unverified
2	FactT5B	BLEU	48.37	—	Unverified
3	JointGT Baseline	BLEU	47.51	—	Unverified
4	FactJointGT	BLEU	47.39	—	Unverified
5	Control Prefixes (T5-large)	METEOR	0.41	—	Unverified
6	T5	METEOR	0.12	—	Unverified
7	BART	METEOR	0.11	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	LeakGAN	BLEU-2	0.95	—	Unverified
2	partGAN	BLEU-2	0.91	—	Unverified
3	RankGAN	BLEU-2	0.85	—	Unverified
4	RelGAN (100)	BLEU-2	0.85	—	Unverified
5	SeqGAN	BLEU-2	0.83	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	LeakGAN	BLEU-2	0.96	—	Unverified
2	PPOGAN	BLEU-2	0.91	—	Unverified
3	RelGAN	BLEU-2	0.88	—	Unverified
4	SeqGAN	BLEU-2	0.86	—	Unverified
5	RankGAN	BLEU-2	0.78	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	UniCRS	Distinct-3	0.65	—	Unverified
2	CRFR	Distinct-3	0.52	—	Unverified
3	KGSF	Distinct-3	0.43	—	Unverified
4	C2CRS	Distinct-3	0.33	—	Unverified
5	KBRD	Distinct-3	0.3	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	UniLM	CIDEr	14.92	—	Unverified
2	BART (TextBox 2.0)	CIDEr	12.98	—	Unverified
3	BART	METEOR	0.3	—	Unverified
4	T5	METEOR	0.29	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Beam search + A*esque (beam)	BLEU-1	34.4	—	Unverified
2	Beam search + A*esque (sample)	BLEU-1	34.4	—	Unverified
3	Beam search + A*esque (greedy)	BLEU-1	34.3	—	Unverified
4	Beam search	BLEU-1	33.7	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	RankGAN	BLEU-2	0.81	—	Unverified
2	SeqGAN	BLEU-2	0.74	—	Unverified
3	LeakGAN	BLEU-2	0.46	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	TGen++	METEOR	0.17	—	Unverified
2	TGen	METEOR	0.15	—	Unverified
3	TGen+	METEOR	0.15	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	GPT2-124M	eval_loss	3.12	—	Unverified
2	GPT2-81M-LOOP	eval_loss	3.11	—	Unverified
3	GPT2-Hermite	eval_loss	2.91	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	LLaMA-65B+CFG (zero-shot)	Accuracy	96.6	—	Unverified
2	LLaMA-30B+CFG (zero-shot)	Accuracy	96.4	—	Unverified
3	LLaMA-13B+CFG (zero-shot)	Accuracy	95.1	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	CNN-VAE	NLL	332.1	—	Unverified
2	SA-VAE	NLL	327.5	—	Unverified
3	Aggressive VAE	NLL	326.7	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	BART (TextBox 2.0)	BLEU-4	10.2	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	STWGAN-GP	BLEU-3	0.62	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	PALM	ROUGE-L	41.41	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	BART (TextBox 2.0)	ROUGE-L	64.34	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	AEM+Attention	BLEU-1	14.17	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	GPT-4	ASR	65.1	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	BART (TextBox 2.0)	ROUGE-L	42.96	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Graph2Seq	BLEU	22	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	WGANGP + DGflow	JS-4	0.19	—	Unverified