awesome-qa
😎 A curated list of the Question Answering (QA)
https://github.com/seriousran/awesome-qa
Last synced: 12 days ago
JSON representation
-
About QA
-
Analysis and Parsing for Pre-processing in QA systems
-
-
Codes
-
Most QA systems have roughly 3 parts
- Paper
- Paper
- BiDAF - Bi-Directional Attention Flow (BIDAF) network is a multi-stage hierarchical process that represents the context at different levels of granularity and uses bi-directional attention flow mechanism to obtain a query-aware context representation without early summarization.
- R-Net - An end-to-end neural networks model for reading comprehension style question answering, which aims to answer questions from a given passage.
- R-Net-in-Keras - R-NET re-implementation in Keras.
- DrQA - DrQA is a system for reading comprehension applied to open-domain question answering.
- BERT - A new language representation model which stands for Bidirectional Encoder Representations from Transformers. Unlike recent language representation models, BERT is designed to pre-train deep bidirectional representations by jointly conditioning on both left and right context in all layers.
- QANet - A Q&A architecture does not require recurrent networks: Its encoder consists exclusively of convolution and self-attention, where convolution models local interactions and self-attention models global interactions.
-
-
Competitions in QA
-
Most QA systems have roughly 3 parts
- Story Cloze Test
- SQuAD
- decaNLP
- DuReader Ver2. - |
- KorQuAD - Kor-Large+ + CLaF (single) | Closed | o |
- KorQuAD 2.0 - baseline(single model) | Opened | x |
- SQuAD 2.0 - Sinitic | ALBERT + DAAF + Verifier (ensemble) | Opened | o |
- TriviaQA - | Closed | - |
- CoQA
-
-
Dataset Collections
-
Most QA systems have roughly 3 parts
-
-
Datasets
-
Facebook AI Research's publication within 5 years
-
Google AI's publication within 5 years
- "QANet: Combining Local Convolution with Global Self-Attention for Reading Comprehension" - Thang Luong, Rui Zhao, Kai Chen, Mohammad Norouzi, Quoc V. Le, ICLR, 2018.
- "Ask the Right Questions: Active Question Reformulation with Reinforcement Learning"
- "Building Large Machine Reading-Comprehension Datasets using Paragraph Vectors"
- "An efficient framework for learning sentence representations"
- "Did the model understand the question?"
- "Analyzing Language Learned by an Active Question Answering Agent"
- "Learning Recurrent Span Representations for Extractive Question Answering"
- "Neural Paraphrase Identification of Questions with Noisy Pretraining"
- "An efficient framework for learning sentence representations"
- "Building Large Machine Reading-Comprehension Datasets using Paragraph Vectors"
- "Did the model understand the question?"
- "Analyzing Language Learned by an Active Question Answering Agent"
- "Learning Recurrent Span Representations for Extractive Question Answering"
- "Neural Paraphrase Identification of Questions with Noisy Pretraining"
-
Most QA systems have roughly 3 parts
-
MS Research's publication within 5 years
- "FigureQA: An Annotated Figure Dataset for Visual Reasoning"
- "Stacked Attention Networks for Image Question Answering"
- "Question Answering with Knowledge Base, Web and Beyond" - tau and Ma, Hao, ACM SIGIR, 2016.
- "NewsQA: A Machine Comprehension Dataset"
- "WIKIQA: A Challenge Dataset for Open-Domain Question Answering" - tau Yih, and Christopher Meek, EMNLP, 2015.
- "Web-based Question Answering: Revisiting AskMSR" - Tse Tsai, Wen-tau Yih, and Christopher J.C. Burges, MSR-TR, 2015.
- "An Overview of Microsoft Deep QA System on Stanford WebQuestions Benchmark" - TR, 2014.
- "Table Cell Search for Question Answering" - tau and Su, Yu and Yan, Xifeng, WWW, 2016.
- "Open Domain Question Answering via Semantic Enrichment" - tau Yih, Chen-Tse Tsai, Jingjing Liu, and Ming-Wei Chang, WWW, 2015.
-
The DeepQA Research Team in IBM Watson's publication within 5 years
- "Unsupervised Entity-Relation Analysis in IBM Watson"
- "WatsonPaths: Scenario-based Question Answering and Inference over Unstructured Information" - Carroll, David A. Ferrucci*, Michael R. Glass, Aditya Kalyanpur, Erik T. Mueller, J. William Murdock, Siddharth Patwardhan, John M. Prager, Christopher A. Welty, IBM Research Report RC25489, 2014.
- "Medical Relation Extraction with Manifold Models"
-
-
Events
-
Most QA systems have roughly 3 parts
-
-
Lectures
-
Most QA systems have roughly 3 parts
- Question Answering - Natural Language Processing - By Dragomir Radev, Ph.D. | University of Michigan | 2016.
- Question Answering - Natural Language Processing - By Dragomir Radev, Ph.D. | University of Michigan | 2016.
-
-
Links
-
Facebook AI Research's publication within 5 years
- Building a Question-Answering System from Scratch— Part 1
- Qeustion Answering with Tensorflow By Steven Hewitt, O'REILLY, 2017
- Why question answering is hard
- Building a Question-Answering System from Scratch— Part 1
- Building a Question-Answering System from Scratch— Part 1
- Building a Question-Answering System from Scratch— Part 1
- Building a Question-Answering System from Scratch— Part 1
- Building a Question-Answering System from Scratch— Part 1
- Building a Question-Answering System from Scratch— Part 1
- Building a Question-Answering System from Scratch— Part 1
- Building a Question-Answering System from Scratch— Part 1
- Building a Question-Answering System from Scratch— Part 1
- Building a Question-Answering System from Scratch— Part 1
- Building a Question-Answering System from Scratch— Part 1
- Building a Question-Answering System from Scratch— Part 1
- Building a Question-Answering System from Scratch— Part 1
- Building a Question-Answering System from Scratch— Part 1
- Building a Question-Answering System from Scratch— Part 1
- Building a Question-Answering System from Scratch— Part 1
- Building a Question-Answering System from Scratch— Part 1
- Building a Question-Answering System from Scratch— Part 1
- Building a Question-Answering System from Scratch— Part 1
- Building a Question-Answering System from Scratch— Part 1
- Building a Question-Answering System from Scratch— Part 1
- Building a Question-Answering System from Scratch— Part 1
- Building a Question-Answering System from Scratch— Part 1
- Building a Question-Answering System from Scratch— Part 1
- Building a Question-Answering System from Scratch— Part 1
- Building a Question-Answering System from Scratch— Part 1
- Building a Question-Answering System from Scratch— Part 1
- Building a Question-Answering System from Scratch— Part 1
- Why question answering is hard
-
-
Publications
-
Most QA systems have roughly 3 parts
- "Learning to Skim Text"
- "Deep Joint Entity Disambiguation with Local Neural Attention" - Eugen Ganea and Thomas Hofmann, 2017.
- "Capturing Semantic Similarity for Entity Linking with Convolutional Neural Networks" - Landau, Greg Durrett and Dan Klei, NAACL-HLT 2016.
- "Entity Linking with a Knowledge Base: Issues, Techniques, and Solutions"
- "Introduction to “This is Watson"
- "A survey on question answering technology from an information retrieval perspective"
- "Question Answering in Restricted Domains: An Overview"
- "Question Answering in Restricted Domains: An Overview"
- "BI-DIRECTIONAL ATTENTION FLOW FOR MACHINE COMPREHENSION"
- "Capturing Semantic Similarity for Entity Linking with Convolutional Neural Networks" - Landau, Greg Durrett and Dan Klei, NAACL-HLT 2016.
- "Entity Linking with a Knowledge Base: Issues, Techniques, and Solutions"
- "Introduction to “This is Watson"
- "Learning to Skim Text"
- "Deep Joint Entity Disambiguation with Local Neural Attention" - Eugen Ganea and Thomas Hofmann, 2017.
- "A survey on question answering technology from an information retrieval perspective"
-
-
Recent Trends
-
AAAI 2020
-
ACL 2019
- Towards Scalable and Reliable Capsule Networks for Challenging NLP Applications
- Cognitive Graph for Multi-Hop Reading Comprehension at Scale
- Real-Time Open-Domain Question Answering with Dense-Sparse Phrase Index
- Unsupervised Question Answering by Cloze Translation
- SemEval-2019 Task 10: Math Question Answering - W 2019, Jun 2019.
- Improving Question Answering over Incomplete KBs with Knowledge-Aware Reader
- Matching Article Pairs with Graphical Decomposition and Convolutions
- Episodic Memory Reader: Learning what to Remember for Question Answering from Streaming Data
- Natural Questions: a Benchmark for Question Answering Research
- Textbook Question Answering with Multi-modal Context Graph Understanding and Self-supervised Open-set Comprehension
- Towards Scalable and Reliable Capsule Networks for Challenging NLP Applications
- Cognitive Graph for Multi-Hop Reading Comprehension at Scale
- Matching Article Pairs with Graphical Decomposition and Convolutions
- SemEval-2019 Task 10: Math Question Answering - W 2019, Jun 2019.
-
Arxiv
- Investigating the Successes and Failures of BERT for Passage Re-Ranking
- BERT with History Answer Embedding for Conversational Question Answering
- Understanding the Behaviors of BERT in Ranking
- BERT Post-Training for Review Reading Comprehension and Aspect-based Sentiment Analysis
- End-to-End Open-Domain Question Answering with BERTserini
- A BERT Baseline for the Natural Questions
- Passage Re-ranking with BERT
- SDNet: Contextualized Attention-based Deep Network for Conversational Question Answering
-
Dataset
-
EMNLP-IJCNLP 2019
- Language Models as Knowledge Bases? - IJCNLP 2019, Sep 2019.
- LXMERT: Learning Cross-Modality Encoder Representations from Transformers - IJCNLP 2019, Dec 2019.
- Answering Complex Open-domain Questions Through Iterative Query Generation - IJCNLP 2019, Oct 2019.
- KagNet: Knowledge-Aware Graph Networks for Commonsense Reasoning - IJCNLP 2019, Sep 2019.
- Mixture Content Selection for Diverse Sequence Generation - IJCNLP 2019, Sep 2019.
- A Discrete Hard EM Approach for Weakly Supervised Question Answering - IJCNLP, 2019, Sep 2019.
- Language Models as Knowledge Bases? - IJCNLP 2019, Sep 2019.
- LXMERT: Learning Cross-Modality Encoder Representations from Transformers - IJCNLP 2019, Dec 2019.
- Answering Complex Open-domain Questions Through Iterative Query Generation - IJCNLP 2019, Oct 2019.
- KagNet: Knowledge-Aware Graph Networks for Commonsense Reasoning - IJCNLP 2019, Sep 2019.
- Mixture Content Selection for Diverse Sequence Generation - IJCNLP 2019, Sep 2019.
- A Discrete Hard EM Approach for Weakly Supervised Question Answering - IJCNLP, 2019, Sep 2019.
-
Recent Language Models
- ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators
- TinyBERT: Distilling BERT for Natural Language Understanding
- MINILM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers
- T5: Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
- ERNIE: Enhanced Language Representation with Informative Entities
- XLNet: Generalized Autoregressive Pretraining for Language Understanding
- ALBERT: A Lite BERT for Self-supervised Learning of Language Representations
- RoBERTa: A Robustly Optimized BERT Pretraining Approach
- DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter
- SpanBERT: Improving Pre-training by Representing and Predicting Spans
- BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
- DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter
- SpanBERT: Improving Pre-training by Representing and Predicting Spans
-
-
Slides
-
Most QA systems have roughly 3 parts
- Question Answering with Knowledge Bases, Web and Beyond - By Scott Wen-tau Yih & Hao Ma | Microsoft Research | 2016.
- Question Answering - By Dr. Mariana Neves | Hasso Plattner Institut | 2017.
-
-
Systems
-
Most QA systems have roughly 3 parts
- Facebook DrQA - Applied to the SQuAD1.0 dataset. The SQuAD2.0 dataset has released. but DrQA is not tested yet.
-
Programming Languages
Categories
Sub Categories
Most QA systems have roughly 3 parts
56
Facebook AI Research's publication within 5 years
39
Google AI's publication within 5 years
14
ACL 2019
14
Recent Language Models
13
EMNLP-IJCNLP 2019
12
MS Research's publication within 5 years
9
Arxiv
8
The DeepQA Research Team in IBM Watson's publication within 5 years
3
AAAI 2020
2
Analysis and Parsing for Pre-processing in QA systems
1
Dataset
1