Reading Comprehension
Most current question answering datasets frame the task as reading comprehension where the question is about a paragraph or document and the answer often is a span in the document. The Machine Reading group at UCL also provides an overview of reading comprehension tasks.
State-of-the-art leaderboards
| Trend | Dataset | Best Method | Paper title | Paper | Code | Compare |
|---|---|---|---|---|---|---|
|
Subtasks
Greatest papers with code
XLNet: Generalized Autoregressive Pretraining for Language Understanding
• huggingface/pytorch-pretrained-BERT
• 
With the capability of modeling bidirectional contexts, denoising autoencoding based pretraining like BERT achieves better performance than pretraining approaches based on autoregressive language modeling.
DOCUMENT RANKING LANGUAGE MODELLING NATURAL LANGUAGE INFERENCE QUESTION ANSWERING READING COMPREHENSION SEMANTIC TEXTUAL SIMILARITY SENTIMENT ANALYSIS TEXT CLASSIFICATION
Language Models are Unsupervised Multitask Learners
Preprint 2019
• huggingface/pytorch-pretrained-BERT
•
Natural language processing tasks, such as question answering, machine translation, reading comprehension, and summarization, are typically approached with supervised learning on taskspecific datasets.
SOTA for Language Modelling on Text8 (using extra training data)
COMMON SENSE REASONING DOCUMENT SUMMARIZATION LANGUAGE MODELLING MACHINE TRANSLATION QUESTION ANSWERING READING COMPREHENSION
RoBERTa: A Robustly Optimized BERT Pretraining Approach
• huggingface/pytorch-transformers
•
Language model pretraining has led to significant performance gains but careful comparison between different approaches is challenging.
LANGUAGE MODELLING LINGUISTIC ACCEPTABILITY NATURAL LANGUAGE INFERENCE QUESTION ANSWERING READING COMPREHENSION SEMANTIC TEXTUAL SIMILARITY SENTIMENT ANALYSIS
AllenNLP: A Deep Semantic Natural Language Processing Platform
This paper describes AllenNLP, a platform for research on deep learning methods in natural language understanding.
Reading Wikipedia to Answer Open-Domain Questions
ACL 2017
• facebookresearch/ParlAI
•
This paper proposes to tackle open- domain question answering using Wikipedia as the unique knowledge source: the answer to any factoid question is a text span in a Wikipedia article.
#115 best model for
Question Answering
on SQuAD1.1
Embracing data abundance: BookTest Dataset for Reading Comprehension
We show that training on the new data improves the accuracy of our Attention-Sum Reader model on the original CBT test data by a much larger margin than many recent attempts to improve the model architecture.
Teaching Machines to Read and Comprehend
NeurIPS 2015
• facebookresearch/ParlAI
•
Teaching machines to read natural language documents remains an elusive challenge.
#13 best model for
Question Answering
on CNN / Daily Mail
Towards AI-Complete Question Answering: A Set of Prerequisite Toy Tasks
One long-term goal of machine learning research is to produce methods that are applicable to reasoning and natural language, in particular building an intelligent dialogue agent.
DuReader: a Chinese Machine Reading Comprehension Dataset from Real-world Applications
WS 2018
• PaddlePaddle/models
• 
Experiments show that human performance is well above current state-of-the-art baseline systems, leaving plenty of room for the community to make improvements.
Bidirectional Attention Flow for Machine Comprehension
Machine comprehension (MC), answering a query about a given context paragraph, requires modeling complex interactions between the context and the query.
#4 best model for
Question Answering
on MS MARCO