This repository contains a list of NLP paper summaries intended to make NLP techniques and topics more approachable and accessible. Work in progress. There is a lot more to be added/improved in the coming days.
If you have blogged about an NLP paper or technique or find an interesting read out there, I encourage you to share with our community. To add your blog posts or summaries to this list just hit on the edit button on this README.md . You can then add your entry by modiying the readme file and submitting a PR which will be reviewed before going live. Alternatively, we can work on transferring the summaries to this repo itself so as to make them more accessible, which is what I am currently doing with some of my own paper summaries below.
If you would like to contribute by blogging about an NLP paper/technique, you can check out our suggestion/guidance at this issue .
And if you need any ideas on how else to contribute to this repo, take a look in the issues section. We are in need of maintainers.
For now, I have adopted a few tracks from ACL for the grouping but this can change based on the granularity of grouping that is needed. Open to ideas here.
Note that we currently provide the source of the where the summary originated from. We are working with a few authors to migrate the content directly to this repo so that summaries are centralized and easily accessible. This also simplifies the way others can contribute to this project. When a summary has been fully migrated to this repo, we will tag the summary as "GitHub" under the "Summary" tab of the tables below to identify them easily.
We are including an extra TL;DR section wherever applicable. This is not meant as a full-fledged summary but rather covers the key points of each paper and serves as a refresher for those who have previously encountered the paper.
If you are facing any issues submitting your PR, just send me an email at [email protected] or DM me on Twitter .
Cognitive Modeling and Psycholinguistics
Title
Summary
Paper Source
Detecting Linguistic Characteristics of Alzheimer’s Dementia by Interpreting Neural Models
dair.ai
Paper
Computational Social Science and Social Media
Title
Summary
Paper Source
Multimodal Classification for Analysing Social Media
dair.ai
Paper
Dialogue and Interactive Systems
Title
Paper Source
TL;DR
Personalizing Dialogue Agents: I have a dog, do you have pets too?
Paper
Richard Csaky
Building a Conversational Agent Overnight with Dialogue Self-Play
Paper
Richard Csaky
Topic-based Evaluation for Conversational Bots
Paper
Richard Csaky
Improving Variational Encoder-Decoders in Dialogue Generation
Paper
Richard Csaky
A Hierarchical Latent Structure for Variational Conversation Modeling
Paper
Richard Csaky
Unsupervised Discrete Sentence Representation Learning for Interpretable Neural Dialog Generation
Paper
Richard Csaky
Sounding Board: A User-Centric and Content-Driven Social Chatbot
Paper
Richard Csaky
DialogWAE: Multimodal Response Generation with Conditional Wasserstein Auto-Encoder
Paper
Richard Csaky
Reinforcing Coherence for Sequence to Sequence Model in Dialogue Generation
Paper
Richard Csaky
Learning to Ask Questions in Open-domain Conversational Systems with Typed Decoders
Paper
Richard Csaky
Multi-turn Dialogue Response Generation in an Adversarial Learning Framework
Paper
Richard Csaky
Zero-Shot Dialog Generation with Cross-Domain Latent Actions
Paper
Richard Csaky
Towards Explainable and Controllable Open Domain Dialogue Generation with Dialogue Acts
Paper
Richard Csaky
Why Do Neural Response Generation Models Prefer Universal Replies?
Paper
Richard Csaky
Aiming to Know You Better Perhaps Makes Me a More Engaging Dialogue Partner
Paper
Richard Csaky
Generating More Interesting Responses in Neural Conversation Models with Distributional Constraints
Paper
Richard Csaky
Adversarial Over-Sensitivity and Over-Stability Strategies for Dialogue Models
Paper
Richard Csaky
Training Millions of Personalized Dialogue Agents
Paper
Richard Csaky
Generating Informative and Diverse Conversational Responses via Adversarial Information Maximization
Paper
Richard Csaky
Better Conversations by Modeling, Filtering, and Optimizing for Coherence and Diversity
Paper
Richard Csaky
A Dataset for Document Grounded Conversations
Paper
Richard Csaky
Talking to myself: self-dialogues as data for conversational agents
Paper
Richard Csaky
Neural Approaches to Conversational AI
Paper
Richard Csaky
Contextual Topic Modeling for Dialog Systems
Paper
Richard Csaky
Automatic Evaluation of Neural Personality-based Chatbots
Paper
Richard Csaky
NEXUS Network: Connecting the Preceding and the Following in Dialogue Generation
Paper
Richard Csaky
MultiWOZ - A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling
Paper
Richard Csaky
The RLLChatbot: a solution to the ConvAI challenge
Paper
Richard Csaky
Neural Response Ranking for Social Conversation: A Data-Efficient Approach
Paper
Richard Csaky
Generating Multiple Diverse Responses for Short-Text Conversation
Paper
Richard Csaky
Wizard of Wikipedia: Knowledge-Powered Conversational agents
Paper
Richard Csaky
Importance of a Search Strategy in Neural Dialogue Modelling
Paper
Richard Csaky
A Study on Dialogue Reward Prediction for Open-Ended Conversational Agents
Paper
Richard Csaky
Title
Paper Source
TL;DR
RUBER: An Unsupervised Method for Automatic Evaluation of Open-Domain Dialog Systems
Paper
Richard Csaky
Adversarial Learning for Neural Dialogue Generation
Paper
Richard Csaky
Hierarchical Recurrent Attention Network for Response Generation
Paper
Richard Csaky
A Copy-Augmented Sequence-to-Sequence Architecture Gives Good Performance on Task-Oriented Dialogue
Paper
Richard Csaky
Generating High-Quality and Informative Conversation Responses with Sequence-to-Sequence Models
Paper
Richard Csaky
A Knowledge-Grounded Neural Conversation Model
Paper
Richard Csaky
Batch Policy Gradient Methods for Improving Neural Conversation Models
Paper
Richard Csaky
Hybrid Code Networks: practical and efficient end-to-end dialog control with supervised and reinforcement learning
Paper
Richard Csaky
Learning Conversational Systems that Interleave Task and Non-Task Content
Paper
Richard Csaky
Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoders
Paper
Richard Csaky
Emotional Chatting Machine: Emotional Conversation Generation with Internal and External Memory
Paper
Richard Csaky
Not All Dialogues are Created Equal: Instance Weighting for Neural Conversational Models
Paper
Richard Csaky
Chat Detection in an Intelligent Assistant: Combining Task-oriented and Non-task-oriented Spoken Dialogue Systems
Paper
Richard Csaky
A Conditional Variational Framework for Dialog Generation
Paper
Richard Csaky
ParlAI: A Dialog Research Software Platform
Paper
Richard Csaky
Emergence of Language with Multi-agent Games: Learning to Communicate with Sequences of Symbols
Paper
Richard Csaky
Generative Encoder-Decoder Models for Task-Oriented Spoken Dialog Systems with Chatting Capability
Paper
Richard Csaky
Personalization in Goal-Oriented Dialog
Paper
Richard Csaky
Natural Language Does Not Emerge ‘Naturally’ in Multi-Agent Dialog
Paper
Richard Csaky
Deal or No Deal? End-to-End Learning for Negotiation Dialogues
Paper
Richard Csaky
DeepProbe: Information Directed Sequence Understanding and Chatbot Design via Recurrent Neural Networks
Paper
Richard Csaky
Enterprise to Computer: Star Trek chatbot
Paper
Richard Csaky
Domain Aware Neural Dialog System
Paper
Richard Csaky
Towards an Automatic Turing Test: Learning to Evaluate Dialogue Responses
Paper
Richard Csaky
A Deep Reinforcement Learning Chatbot
Paper
Richard Csaky
Challenging Neural Dialogue Models with Natural Data: Memory Networks Fail on Incremental Phenomena
Paper
Richard Csaky
Flexible End-to-End Dialogue System for Knowledge Grounded Conversation
Paper
Richard Csaky
Edina: Building an Open Domain Socialbot with Self-dialogues
Paper
Richard Csaky
Interactive Policy Learning In End-to-End Trainable Task-Oriented Neural Dialog Models
Paper
Richard Csaky
Augmenting End-to-End Dialog Systems with Commonsense Knowledge
Paper
Richard Csaky
Multi-Task Learning for Speaker-Role Adaptation in Neural Conversation Models
Paper
Richard Csaky
DailyDialog: A Manually Labelled Multi-turn Dialogue Dataset
Paper
Richard Csaky
A Dual Encoder Sequence to Sequence Model for Open-Domain Dialogue Modeling
Paper
Richard Csaky
Adversarial Advantage Actor-Critic Model For Task-Completion Dialogue Policy Learning
Paper
Richard Csaky
Customized Nonlinear Bandits for Online Response Selection in Neural Conversation Models
Paper
Richard Csaky
End-to-end Adversarial Learning for Generative Conversational Agents
Paper
Richard Csaky
Fine Grained Knowledge Transfer for Personalized Task-oriented Dialogue Systems
Paper
Richard Csaky
BBQ-Networks: Efficient Exploration in Deep Reinforcement Learning for Task-Oriented Dialogue Systems
Paper
Richard Csaky
End-to-End Optimization of Task-Oriented Dialogue Model with Deep Reinforcement Learning
Paper
Richard Csaky
Are You Talking to Me? Reasoned Visual Dialog Generation through Adversarial Learning
Paper
Richard Csaky
RubyStar: A Non-Task-Oriented Mixture Model Dialog System
Paper
Richard Csaky
Examining Cooperation in Visual Dialog Models
Paper
Richard Csaky
Why Do Neural Dialog Systems Generate Short and Meaningless Replies? A Comparison between Dialog and Translation
Paper
Richard Csaky
End-to-End Offline Goal-Oriented Dialog Policy Learning via Policy Gradient
Paper
Richard Csaky
Toward Continual Learning for Conversational Agents
Paper
Richard Csaky
An Ensemble Model with Ranking for Social Dialogue
Paper
Richard Csaky
Title
Paper Source
TL;DR
Incorporating Copying Mechanism in Sequence-to-Sequence Learning
Paper
Richard Csaky
A Persona-Based Neural Conversation Model
Paper
Richard Csaky
How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generation
Paper
Richard Csaky
StalemateBreaker: A Proactive Content-Introducing Approach to Automatic Human-Computer Conversation
Paper
Richard Csaky
A Network-based End-to-End Trainable Task-oriented Dialogue System
Paper
Richard Csaky
A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialogues
Paper
Richard Csaky
Deep Reinforcement Learning for Dialogue Generation
Paper
Richard Csaky
An Attentional Neural Conversation Model with Improved Specificity
Paper
Richard Csaky
Topic Aware Neural Response Generation
Paper
Richard Csaky
Multiresolution Recurrent Neural Networks: An Application to Dialogue Response Generation
Paper
Richard Csaky
Neural Discourse Modeling of Conversations
Paper
Richard Csaky
Neural Contextual Conversation Learning with Labeled Question-Answering Pairs
Paper
Richard Csaky
Sequence to Backward and Forward Sequences: A Content-Introducing Approach to Generative Short-Text Conversation
Paper
Richard Csaky
Two are Better than One: An Ensemble of Retrieval- and Generation-Based Dialog Systems
Paper
Richard Csaky
Dialogue Learning With Human-In-The-Loop
Paper
Richard Csaky
Deep Active Learning for Dialogue Generation
Paper
Richard Csaky
Title
Paper Source
TL;DR
Neural Responding Machine for Short-Text Conversation
Paper
Richard Csaky
A Neural Conversational Model
Paper
Richard Csaky
A Neural Network Approach to Context-Sensitive Generation of Conversational Responses
Paper
Richard Csaky
Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models
Paper
Richard Csaky
A Diversity-Promoting Objective Function for Neural Conversation Models
Paper
Richard Csaky
Attention with Intention for a Neural Network Conversation Model
Paper
Richard Csaky
A Survey of Available Corpora for Building Data-Driven Dialogue Systems
Paper
Richard Csaky
Title
Summary
Paper Source
Defending Against Neural Fake News
Ai2 Blog
Paper
Title
Summary
Paper Source
Troubling Trends in Machine Learning Scholarship
dair.ai
Paper
Examining Gender and Race Bias in Two Hundred Sentiment Analysis Systems
dair.ai
Paper
Title
Summary
Paper Source
Encode, Tag, Realize: High-Precision Text Editing
Google AI Blog
Paper
Title
Paper Source
TL;DR
Latent Predictor Networks for Code Generation
Paper
Richard Csaky
Interpretability and Analysis of Models for NLP
Title
Summary
Paper Source
Olive Oil is Made of Olives, Baby Oil is Made for Babies: Interpreting Noun Compounds using Paraphrases in a Neural Model
dair.ai
Paper
Title
Summary
Paper Source
TL;DR
Language Models are Unsupervised Multitask Learners
-
Paper
Richard Csaky
Plug and Play Language Models: A Simple Approach to Controlled Text Generation
Uber Engineering
Paper
-
ALBERT: A Lite BERT for Self-Supervised Learning Of Language Representations
Amit Chaudhary
Paper
-
Fine-Tuning GPT-2 from Human Preferences
Open AI
Paper
-
XLNet: Generalized Autoregressive Pretraining for Language Understanding
dair.ai
Paper
-
Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context
dair.ai
Paper
-
Title
Paper Source
TL;DR
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Paper
Richard Csaky
Title
Paper Source
TL;DR
Beyond BLEU: Training Neural Machine Translation with Semantic Similarity
Paper
Richard Csaky
Title
Paper Source
TL;DR
Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation
Paper
Richard Csaky
Sequence to Sequence Learning with Neural Networks
Paper
Richard Csaky
Neural Machine Translation by Jointly Learning to Align and Translate
Paper
Richard Csaky
Title
Summary
Paper Source
A Hierarchical Multi-task Approach for Learning Embeddings from Semantic Tasks
dair.ai
Paper
Title
Summary
Paper Source
nocaps: novel object captioning at scale
dair.ai
Paper
Sentiment Analysis, Stylistic Analysis, and Argument Mining
Title
Summary
Paper Source
Emotion-Cause Pair Extraction: A New Task to Emotion Analysis in Texts
dair.ai
Paper
Title
Summary
Paper Source
DialogueRNN: An Attentive RNN for Emotion Detection in Conversations
dair.ai
Paper
Exploring Emoji Usage and Prediction Through a Temporal Variation Lens
dair.ai
Paper
Title
Summary
Paper Source
Context-Dependent Sentiment Analysis in User-Generated Videos
dair.ai
Paper
Title
Summary
Paper Source
A Deeper Look into Sarcastic Tweets Using Deep Convolutional Neural Networks
dair.ai
Paper
Title
Summary
Paper Source
Get To The Point: Summarization with Pointer-Generator Networks
Abigail See
Paper
Title
Paper Source
TL;DR
Abstractive Text Summarization using Sequence-to-sequence RNNs and Beyond
Paper
Richard Csaky
Overviews / Surveys / Highlights
Title
Summary
Paper Source
Generalized Language Models
Lilian Weng
-
10 ML & NLP Research Highlights of 2019
Sebastian Ruder
-
Google Research: Looking Back at 2019, and Forward to 2020 and Beyond
Google AI Blog
-
NLP Year in Review — 2019
dair.ai
-
Title
Summary
Paper Source
A Light Introduction to Transfer Learning for NLP
dair.ai
-
Attention? Attention!
Lilian Weng
-
Title
Summary
Paper Source
Recent Trends in Deep Learning Based Natural Language Processing
dair.ai
Paper
Miscellaneous (To be categorized)
Title
Summary
Paper Source
Parameter-Efficient Transfer Learning for NLP
dair.ai
Paper