Natural-Language-Generation.md

Natural Language Generation

Non-Autoregressive Decoding Slides

VAE

1. A Semantically Consistent and Syntactically Variational Encoder-Decoder Framework for Paraphrase Generation Wenqing Chen, Jidong Tian, Liqiang Xiao, Hao He, Yaohui Jin COLING20 [pdf]

Knowledge

Paper	Conference
Modeling Global and Local Node Contexts for Text Generation from Knowledge Graphs
Text Generation from Knowledge Graphs with Graph Transformers	NAACL19
The WebNLG Challenge: Generating Text from RDF Data	INLG17

Knowledge-Enhanced

Paper	Conference
Improving Knowledge-aware Dialogue Generation via Knowledge Base Question Answering	AAAI20
A Knowledge-Enhanced Pretraining Model for Commonsense Story Generation	TACL19
Story Ending Generation with Incremental Encoding and Commonsense Knowledge	AAAI19
Commonsense Knowledge Aware Conversation Generation with Graph Attention	IJCAI 2018

Event

Paper	Conference	Highlights
Enhancing Dialog Coherence with Event Graph Grounded Content Planning	IJCAI20	event graph + reinforcement learning
Open Domain Event Text Generation	AAAI20

Question Generation

Paper	Conference
Talk to Papers: Bringing Neural Question Answering to Academic Search	ACL2020
QURIOUS: Question Generation Pretraining for Text Generation	ACL20
Syn-QG Syntactic and Shallow Semantic Rules for Question Generation	ACL20
Reinforcement Learning Based Graph-to-Sequence Model for Natural Question Generation	ICLR20
Interconnected Question Generation with Coreference Alignment and Conversation Flow Modeling	ACL19
Let’s Ask Again: Refine Network for Automatic Question Generation	EMNLP19
Reinforced Dynamic Reasoning for Conversational Question Generation	ACL19
Mixture Content Selection for Diverse Sequence Generation	EMNLP19
Reinforced Dynamic Reasoning for Conversational Question Generation	ACL19

Multi-stages Generation

Paper	Conference	Highlights
PAIR: Planning and Iterative Refinement in Pre-trained Transformers for Long Text Generation	EMNLP20
Generate, Delete and Rewrite : A Three-Stage Framework for Improving Persona Consistency of Dialogue Generation	ACL20
Exclusive Hierarchical Decoding for Deep Keyphrase Generation	ACL20	hierarchical decoding
Learning to Predict Explainable Plots for Neural Story Generation
Encode, Tag, Realize: High-Precision Text Editing	EMNLP19
Automatic Dialogue Summary Generation for Customer Service	KDD19
Let’s Ask Again: Refine Network for Automatic Question Generation	EMNLP19
Generating Long and Informative Reviews with Aspect-Aware Coarse-to-Fine Decoding	ACL19
Strategies for Structuring Story Generation	ACL19
Plan-And-Write: Towards Better Automatic Storytelling	AAAI19
A Skeleton-Based Model for Promoting Coherence Among Sentences in Narrative Story Generation	EMNLP18
Hierarchical Neural Story Generation	ACL18

Non-autoregressive

1. Directed Acyclic Transformer for Non-Autoregressive Machine Translation Fei Huang, Hao Zhou, Yang Liu, Hang Li, Minlie Huang ICML 2022 [pdf]
2. A Survey on Non-Autoregressive Generation for Neural Machine Translation and Beyond Yisheng Xiao, Lijun Wu, Junliang Guo, Juntao Li, Min Zhang, Tao Qin, Tie-yan Liu [pdf]
3. switch-GLAT: Multilingual Parallel Machine Translation Via Code-Switch Decoder Zhenqiao Song, Hao Zhou, Lihua Qian, Jingjing Xu, Shanbo Cheng, Mingxuan Wang, Lei Li ICLR 2022 [pdf]
4. Glancing Transformer for Non-Autoregressive Neural Machine Translation Lihua Qian, Hao Zhou, Yu Bao, Mingxuan Wang, Lin Qiu, Weinan Zhang, Yong Yu, Lei Li ACL 2021 [pdf] [code1] [code2]
5. Non-Autoregressive Text Generation with Pre-trained Language Models Yixuan Su, Deng Cai, Yan Wang, David Vandyke, Simon Baker, Piji Li, Nigel Collier EACL21 [pdf] [code]
6. Incorporating a Local Translation Mechanism into Non-autoregressive Translation Xiang Kong, Zhisong Zhang, Eduard Hovy EMNLP20 [pdf] [code]

Paper	Conference
Lexically Constrained Neural Machine Translation with Levenshtein Transformer	ACL20 short
Mask-Predict: Parallel Decoding of Conditional Masked Language Models	EMNLP19
Levenshtein Transformer
Insertion-based Decoding with automatically Inferred Generation Order
KERMIT: Generative Insertion-Based Modeling for Sequences
Non-Monotonic Sequential Text Generation	ICML19
Insertion Transformer: Flexible Sequence Generation via Insertion Operations	ICML19
Sequence Generation: From Both Sides to the Middle	IJCAI19
Correct-and-Memorize:Learning to Translate from Interactive Revisions	IJCAI19
Non-Autoregressive Neural Machine Translation	ICLR18
The Importance of Generation Order in Language Modeling	EMNLP18

New model

Paper	Conference
MacNet: Transferring Knowledge from Machine Comprehension to Sequence-to-Sequence Models	NIPS18

Incremental

Paper	Conference
Incremental Transformer with Deliberation Decoder for Document Grounded Conversations	ACL19
Story Ending Generation with Incremental Encoding and Commonsense Knowledge	AAAI19

Poetry Generation

Paper	Conference
Generating Major Types of Chinese Classical Poetry in a Uniformed Framework
Generating Chinese Poetry from Images via Concrete and Abstract Information	IJCNN 2020
MixPoet: Diverse Poetry Generation via Learning Controllable Mixed Latent Space	AAAI20

Controlled

Paper	Conference	Highlights
Rigid Formats Controlled Text Generation	ACL20	make use of input embedding

Keyphrase Generation

Paper	Conference	Highlights
Exclusive Hierarchical Decoding for Deep Keyphrase Generation	ACL20	hierarchical decoding

Table2Text

1. Dynamic Topic Tracker for KB-to-Text Generation Zihao Fu, Lidong Bing, Wai Lam, Shoaib Jameel COLING20 [pdf]
2. Learning with Contrastive Examples for Data-to-Text Generation Yui Uehara, Tatsuya Ishigaki, Kasumi Aoki, Hiroshi Noji, Keiichi Goshima, Ichiro Kobayashi, Hiroya Takamura, Yusuke Miyao COLING20 [pdf] [code]

Paper	Conference
Logical Natural Language Generation from Open-Domain Tables	ACL20

Evaluation

Paper	Conference
MoverScore: Text Generation Evaluating with Contextualized Embeddings and Earth Mover Distance	EMNLP19
BERTScore: Evaluating Text Generation with BERT	ICLR2020
VizSeq: A Visual Analysis Toolkit for Text Generation Tasks

Other

Paper	Conference
TLDR: Token Loss Dynamic Reweighting for Reducing Repetitive Utterance Generation
Plug and Play Language Model- A Simple Baseline for Controlled Language Generation	ICLR20
PaperRobot: Incremental Draft Generation of Scientific Ideas	ACL19
Hierarchical Recurrent Attention Network for Response Generation	AAAI18