Question Answering

2752 papers with code • 143 benchmarks • 358 datasets

Question Answering is the task of answering questions (typically reading comprehension questions), but abstaining when presented with a question that cannot be answered based on the provided context.

Question answering can be segmented into domain-specific tasks like community question answering and knowledge-base question answering. Popular benchmark datasets for evaluation question answering systems include SQuAD, HotPotQA, bAbI, TriviaQA, WikiQA, and many others. Models for question answering are typically evaluated on metrics like EM and F1. Some recent top performing models are T5 and XLNet.

( Image credit: SQuAD )

Libraries

Use these libraries to find Question Answering models and implementations
29 papers
122,310
5 papers
2,550
See all 10 libraries.

Most implemented papers

Attention Is All You Need

tensorflow/tensor2tensor NeurIPS 2017

The dominant sequence transduction models are based on complex recurrent or convolutional neural networks in an encoder-decoder configuration.

BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

google-research/bert NAACL 2019

We introduce a new language representation model called BERT, which stands for Bidirectional Encoder Representations from Transformers.

Graph Attention Networks

PetarV-/GAT ICLR 2018

We present graph attention networks (GATs), novel neural network architectures that operate on graph-structured data, leveraging masked self-attentional layers to address the shortcomings of prior methods based on graph convolutions or their approximations.

RoBERTa: A Robustly Optimized BERT Pretraining Approach

pytorch/fairseq 26 Jul 2019

Language model pretraining has led to significant performance gains but careful comparison between different approaches is challenging.

Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer

huggingface/transformers arXiv 2019

Transfer learning, where a model is first pre-trained on a data-rich task before being fine-tuned on a downstream task, has emerged as a powerful technique in natural language processing (NLP).

ALBERT: A Lite BERT for Self-supervised Learning of Language Representations

google-research/ALBERT ICLR 2020

Increasing model size when pretraining natural language representations often results in improved performance on downstream tasks.

Deep contextualized word representations

flairNLP/flair NAACL 2018

We introduce a new type of deep contextualized word representation that models both (1) complex characteristics of word use (e. g., syntax and semantics), and (2) how these uses vary across linguistic contexts (i. e., to model polysemy).

Language Models are Few-Shot Learners

openai/gpt-3 NeurIPS 2020

By contrast, humans can generally perform a new language task from only a few examples or from simple instructions - something which current NLP systems still largely struggle to do.

End-To-End Memory Networks

facebook/MemNN NeurIPS 2015

For the former our approach is competitive with Memory Networks, but with less supervision.

BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension

huggingface/transformers ACL 2020

We evaluate a number of noising approaches, finding the best performance by both randomly shuffling the order of the original sentences and using a novel in-filling scheme, where spans of text are replaced with a single mask token.