The compendium is created with an objective to organise all the latest research carried in the direction of NLP, so that interested researchers, students can head directly to papers that matter rather than sauntering through the conference website and face information overload.

NLP top 10 conferences Compendium

Most Cited 100 Papers (In Last 3 Years)

Title	Citation	Conference
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding	21031	NAACL2019
Transformer-XL: Attentive Language Models beyond a Fixed-Length Context	1233	ACL2019
BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension	998	ACL2020
Unsupervised Cross-lingual Representation Learning at Scale	813	ACL2020
Energy and Policy Considerations for Deep Learning in NLP	713	ACL2019
Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks	703	EMNLP2019
SciBERT: A Pretrained Language Model for Scientific Text	571	EMNLP2019
Multi-Task Deep Neural Networks for Natural Language Understanding	533	ACL2019
LXMERT: Learning Cross-Modality Encoder Representations from Transformers	452	EMNLP2019
BERT Rediscovers the Classical NLP Pipeline	436	ACL2019
A Structural Probe for Finding Syntax in Word Representations	407	NAACL2019
How Multilingual is Multilingual BERT?	404	ACL2019
Text Summarization with Pretrained Encoders	402	EMNLP2019
Attention is not Explanation	390	NAACL2019
EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Tasks	364	EMNLP2019
Don’t Stop Pretraining: Adapt Language Models to Domains and Tasks	362	ACL2020
ERNIE: Enhanced Language Representation with Informative Entities	362	ACL2019
Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference	359	ACL2019
Language Models as Knowledge Bases?	349	EMNLP2019
What Does BERT Learn about the Structure of Language?	342	ACL2019
Linguistic Knowledge and Transferability of Contextual Representations	317	NAACL2019
Predicting the Type and Target of Offensive Posts in Social Media	286	NAACL2019
Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned	280	ACL2019
Beto, Bentz, Becas: The Surprising Cross-Lingual Effectiveness of BERT	258	EMNLP2019
Dense Passage Retrieval for Open-Domain Question Answering	255	EMNLP2020
Attention is not not Explanation	245	EMNLP2019
DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs	235	NAACL2019
CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge	235	NAACL2019
Latent Retrieval for Weakly Supervised Open Domain Question Answering	231	ACL2019
Knowledge Enhanced Contextual Word Representations	218	EMNLP2019
COMET: Commonsense Transformers for Automatic Knowledge Graph Construction	217	ACL2019
The Risk of Racial Bias in Hate Speech Detection	215	ACL2019
Patient Knowledge Distillation for BERT Model Compression	211	EMNLP2019
Matching the Blanks: Distributional Similarity for Relation Learning	204	ACL2019
Revealing the Dark Secrets of BERT	196	EMNLP2019
Probing Neural Network Comprehension of Natural Language Arguments	192	ACL2019
CamemBERT: a Tasty French Language Model	188	ACL2020
Universal Adversarial Triggers for Attacking and Analyzing NLP	188	EMNLP2019
BERT Post-Training for Review Reading Comprehension and Aspect-based Sentiment Analysis	184	NAACL2019
On the Cross-lingual Transferability of Monolingual Representations	180	ACL2020
Adversarial NLI: A New Benchmark for Natural Language Understanding	170	ACL2020
Justifying Recommendations using Distantly-Labeled Reviews and Fine-Grained Aspects	168	EMNLP2019
Massively Multilingual Neural Machine Translation	167	NAACL2019
Beyond Accuracy: Behavioral Testing of NLP Models with CheckList	165	ACL2020
Utilizing BERT for Aspect-Based Sentiment Analysis via Constructing Auxiliary Sentence	165	NAACL2019
Towards Empathetic Open-domain Conversation Models: A New Benchmark and Dataset	162	ACL2019
Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systems	161	ACL2019
Is Attention Interpretable?	161	ACL2019
TuckER: Tensor Factorization for Knowledge Graph Completion	160	EMNLP2019
Pooled Contextualized Embeddings for Named Entity Recognition	160	NAACL2019
BLEURT: Learning Robust Metrics for Text Generation	158	ACL2020
Learning Deep Transformer Models for Machine Translation	158	ACL2019
Designing and Interpreting Probes with Control Tasks	154	EMNLP2019
Mask-Predict: Parallel Decoding of Conditional Masked Language Models	152	EMNLP2019
Language (Technology) is Power: A Critical Survey of “Bias” in NLP	151	ACL2020
How Contextual are Contextualized Word Representations? Comparing the Geometry of BERT, ELMo, and GPT-2 Embeddings	151	EMNLP2019
MELD: A Multimodal Multi-Party Dataset for Emotion Recognition in Conversations	147	ACL2019
HIBERT: Document Level Pre-training of Hierarchical Bidirectional Transformers for Document Summarization	140	ACL2019
How Much Knowledge Can You Pack Into the Parameters of a Language Model?	138	EMNLP2020
HellaSwag: Can a Machine Really Finish Your Sentence?	138	ACL2019
KagNet: Knowledge-Aware Graph Networks for Commonsense Reasoning	137	EMNLP2019
Gender Bias in Contextualized Word Embeddings	136	NAACL2019
Attention Guided Graph Convolutional Networks for Relation Extraction	134	ACL2019
Generating Natural Language Adversarial Examples through Probability Weighted Word Saliency	133	ACL2019
75 Languages, 1 Model: Parsing Universal Dependencies Universally	133	EMNLP2019
MuST-C: a Multilingual Speech Translation Corpus	133	NAACL2019
Adaptive Attention Span in Transformers	128	ACL2019
Cloze-driven Pretraining of Self-attention Networks	127	EMNLP2019
MobileBERT: a Compact Task-Agnostic BERT for Resource-Limited Devices	126	ACL2020
A Corpus for Reasoning about Natural Language Grounded in Photographs	126	ACL2019
The FLORES Evaluation Datasets for Low-Resource Machine Translation: Nepali–English and Sinhala–English	126	EMNLP2019
Explain Yourself! Leveraging Language Models for Commonsense Reasoning	125	ACL2019
BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions	125	NAACL2019
Social IQa: Commonsense Reasoning about Social Interactions	124	EMNLP2019
On Measuring Social Biases in Sentence Encoders	124	NAACL2019
MLQA: Evaluating Cross-lingual Extractive Question Answering	123	ACL2020
Mitigating Gender Bias in Natural Language Processing: Literature Review	123	ACL2019
Text Generation from Knowledge Graphs with Graph Transformers	123	NAACL2019
BERT for Coreference Resolution: Baselines and Analysis	122	EMNLP2019
Learning Attention-based Embeddings for Relation Prediction in Knowledge Graphs	121	ACL2019
Cross-Lingual Alignment of Contextual Word Embeddings, with Applications to Zero-shot Dependency Parsing	121	NAACL2019
Question Answering by Reasoning Across Documents with Graph Convolutional Networks	120	NAACL2019
Multimodal Transformer for Unaligned Multimodal Language Sequences	117	ACL2019
Entity, Relation, and Event Extraction with Contextualized Span Representations	117	EMNLP2019
Towards Complex Text-to-SQL in Cross-Domain Database with Intermediate Representation	116	ACL2019
Hierarchical Transformers for Multi-Document Summarization	116	ACL2019
Don’t Take the Easy Way Out: Ensemble Based Methods for Avoiding Known Dataset Biases	114	EMNLP2019
Are We Modeling the Task or the Annotator? An Investigation of Annotator Bias in Natural Language Understanding Datasets	113	EMNLP2019
Show Your Work: Improved Reporting of Experimental Results	113	EMNLP2019
Cyclical Annealing Schedule: A Simple Approach to Mitigating KL Vanishing	113	NAACL2019
Multi-News: A Large-Scale Multi-Document Summarization Dataset and Abstractive Hierarchical Model	112	ACL2019
MoverScore: Text Generation Evaluating with Contextualized Embeddings and Earth Mover Distance	112	EMNLP2019
A Unified MRC Framework for Named Entity Recognition	109	ACL2020
WiC: the Word-in-Context Dataset for Evaluating Context-Sensitive Meaning Representations	109	NAACL2019
Evaluating the Factual Consistency of Abstractive Text Summarization	107	EMNLP2020
Neural Text Summarization: A Critical Evaluation	107	EMNLP2019
What makes a good conversation? How controllable attributes affect human judgments	107	NAACL2019
Disentangled Representation Learning for Non-Parallel Text Style Transfer	104	ACL2019
How to (Properly) Evaluate Cross-Lingual Word Embeddings: On Strong Baselines, Comparative Analyses, and Some Misconceptions	104	ACL2019
Cosmos QA: Machine Reading Comprehension with Contextual Commonsense Reasoning	104	EMNLP2019

1. ACL:

Papers Call 2020:

https://acl2020.org/calls/papers/

ACL 2019:

Best Demo papers:

Emotion-Cause Pair Extraction: A New Task to Emotion Analysis in Texts. Rui Xia and Zixiang Ding

A Simple Theoretical Model of Importance for Summarization Maxime Peyrard

Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systems Chien-Sheng Wu, Andrea Madotto, Ehsan Hosseini-Asl, Caiming Xiong, Richard Socher and Pascale Fung

We need to talk about standard splits Kyle Gorman and Steven Bedrick

Zero-shot Word Sense Disambiguation using Sense Definition Embeddings Sawan Kumar, Sharmistha Jat, Karan Saxena and Partha Talukdar

Best short paper:

Do you know that Florence is packed with visitors? Evaluating state-of-the-art models of speaker commitment. Nanjiang Jiang and Marie-Catherine de Marneffe

Best long paper:

Bridging the Gap between Training and Inference for Neural Machine Translation. Wen Zhang, Yang Feng, Fandong Meng, Di You and Qun Liu

Nominated Best papers:

Title: Detecting Concealed Information in Text and Speech Authors: Shengli Hu

Title: AMR Parsing as Sequence-to-Graph Transduction. Authors: Sheng Zhang, Xutai Ma, Kevin Duh and Benjamin Van Durme

Title: Do Neural Dialog Systems Use the Conversation History Effectively? An Empirical Study. Authors: Chinnadhurai Sankar, Sandeep Subramanian, Chris Pal, Sarath Chandar and Yoshua Bengio

Title: Transferable Multi-Domain State Generator for Task-Oriented Authors: Chien-Sheng Wu, Andrea Madotto, Ehsan Hosseini-Asl, Caiming Xiong, Richard Socher and Pascale Fung

Title: Emotion-Cause Pair Extraction: A New Task to Emotion Analysis in Texts. Authors: Rui Xia and Zixiang Ding

Title: ConvLab: Multi-Domain End-to-End Dialog System Platform Authors: Sungjin Lee, Qi Zhu, Ryuichi Takanobu, Zheng Zhang, Yaoqin Zhang, Xiang Li, Jinchao Li, Baolin Peng, Xiujun Li, Minlie Huang and Jianfeng Gao

Title: Studying Summarization Evaluation Metrics in the Appropriate Scoring Range Author: Maxime Peyrard

Title: Persuasion for Good: Towards a Personalized Persuasive Dialogue System for Social Good. Authors: Xuewei Wang, Weiyan Shi, Richard Kim, Yoojung Oh, Sijia Yang, Jingwen Zhang and Zhou Yu

Title: Zero-Shot Entity Linking by Reading Entity Descriptions Authors: Lajanugen Logeswaran, Ming-Wei Chang, Kenton Lee, Kristina Toutanova, Jacob Devlin and Honglak Lee

Table of accepted Tutorials:

Table of accepted Tutorials:
T1: Latent Structure Models for Natural Language Processing
T2: Graph-Based Meaning Representations: Design and Processing
T3: Discourse Analysis and Its Applications
T4: Computational Analysis of Political Texts: Bridging Research Efforts Across Communities
T5: Wikipedia as a Resource for Text Analysis and Retrieval
T6: Deep Bayesian Natural Language Processing
T7: Unsupervised Cross-Lingual Representation Learning
T8: Advances in Argument Mining
T9: Storytelling from Structured Data and Knowledge Graphs : An NLG Perspective

List of Workshops:

NLP for Conversational AI

BioNLP 2019

Second Workshop on Storytelling (StoryNLP)

4th Workshop on Representation Learning for NLP (RepL4NLP-2019)

All papers:

Proceedings all Papers 661 papers
Student Reasearch Workshop 61 papers
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: System Demonstrations 35 papers
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: Tutorial Abstracts 10 papers

ACL 2018:

Best Demo Paper:

Out-of-the-box Universal Romanization Tool by Ulf Hermjakob, Jonathan May and Kevin Knight

Best Short papers:

Know What You Don’t Know: Unanswerable Questions for SQuAD. Pranav Rajpurkar, Robin Jia and Percy Liang
‘Lighter’ Can Still Be Dark: Modeling Comparative Color Descriptions. Olivia Winn and Smaranda Muresan

Best Long papers:

Finding syntax in human encephalography with beam search. John Hale, Chris Dyer, Adhiguna Kuncoro and Jonathan Brennan.
Learning to Ask Good Questions: Ranking Clarification Questions using Neural Expected Value of Perfect Information. Sudha Rao and Hal Daumé III.
Let’s do it “again”: A First Computational Approach to Detecting Adverbial Presupposition Triggers. Andre Cianflone,* Yulan Feng,* Jad Kabbara* and Jackie Chi Kit Cheung.

Best Paper Honourable Mentions:

Short Papers

Jointly Predicting Predicates and Arguments in Neural Semantic Role Labeling. Luheng He, Kenton Lee, Omer Levy and Luke Zettlemoyer.
Do Neural Network Cross-Modal Mappings Really Bridge Modalities? Guillem Collell and Marie-Francine Moens.

Long Papers

Coarse-to-Fine Decoding for Neural Semantic Parsing. Li Dong and Mirella Lapata.
NASH: Toward End-to-End Neural Architecture for Generative Semantic Hashing. Dinghan Shen, Qinliang Su, Paidamoyo Chapfuwa, Wenlin Wang, Guoyin Wang, Ricardo Henao and Lawrence Carin.
Backpropagating through Structured Argmax using a SPIGOT. Hao Peng, Sam Thomson and Noah A. Smith.
Hierarchical Neural Story Generation. Angela Fan, Mike Lewis and Yann Dauphin.
Semantically Equivalent Adversarial Rules for Debugging NLP models. Marco Tulio Ribeiro, Sameer Singh and Carlos Guestrin.
Large-Scale QA-SRL Parsing. Nicholas FitzGerald, Julian Michael, Luheng He and Luke Zettlemoyer.

Table of accepted Tutorials:

T1: 100 Things You Always Wanted to Know about Semantics & Pragmatics But Were Afraid to Ask
T2: Neural Approaches to Conversational AI
T3: Variational Inference and Deep Generative Models
T4: Connecting Language and Vision to Actions
T5: Beyond Multiword Expressions: Processing Idioms and Metaphors
T6: Neural Semantic Parsing
T7: Deep Reinforcement Learning for NLP
T8: Multi-lingual Entity Discovery and Linking