Natural Language Processing
 
Edit

Question Answering

2900 papers with code • 131 benchmarks • 362 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
huggingface/transformers
27 papers
125,290
facebookresearch/ParlAI
5 papers
10,431
dmlc/gluon-nlp
5 papers
2,549
faceonlive/ai-research
5 papers
179
See all 11 libraries.

Datasets

Subtasks

Most implemented papers

Most implemented Social Latest No code

SQuAD: 100,000+ Questions for Machine Comprehension of Text

worksheets/0xd53d03a4 • EMNLP 2016

We present the Stanford Question Answering Dataset (SQuAD), a new reading comprehension dataset consisting of 100, 000+ questions posed by crowdworkers on a set of Wikipedia articles, where the answer to each question is a segment of text from the corresponding reading passage.

19
Paper
Code

BioBERT: a pre-trained biomedical language representation model for biomedical text mining

dmis-lab/biobert • • 25 Jan 2019

Biomedical text mining is becoming increasingly important as the number of biomedical documents rapidly grows.

19
Paper
Code

Language Models are Unsupervised Multitask Learners

openai/gpt-2 • • Preprint 2019

Natural language processing tasks, such as question answering, machine translation, reading comprehension, and summarization, are typically approached with supervised learning on taskspecific datasets.

17
Paper
Code

ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators

google-research/electra • • ICLR 2020

Then, instead of training a model that predicts the original identities of the corrupted tokens, we train a discriminative model that predicts whether each token in the corrupted input was replaced by a generator sample or not.

17
Paper
Code

Dense Passage Retrieval for Open-Domain Question Answering

facebookresearch/DPR • • EMNLP 2020

Open-domain question answering relies on efficient passage retrieval to select candidate contexts, where traditional sparse vector space models, such as TF-IDF or BM25, are the de facto method.

17
Paper
Code

QANet: Combining Local Convolution with Global Self-Attention for Reading Comprehension

BangLiu/QANet-PyTorch • • ICLR 2018

On the SQuAD dataset, our model is 3x to 13x faster in training and 4x to 9x faster in inference, while achieving equivalent accuracy to recurrent models.

15
Paper
Code

Reformer: The Efficient Transformer

google/trax • • ICLR 2020

Large Transformer models routinely achieve state-of-the-art results on a number of tasks but training these models can be prohibitively costly, especially on long sequences.

15
Paper
Code

ERNIE: Enhanced Representation through Knowledge Integration

PaddlePaddle/PaddleNLP • • 19 Apr 2019

We present a novel language representation model enhanced by knowledge called ERNIE (Enhanced Representation through kNowledge IntEgration).

14
Paper
Code

Llama 2: Open Foundation and Fine-Tuned Chat Models

facebookresearch/llama • • 18 Jul 2023

In this work, we develop and release Llama 2, a collection of pretrained and fine-tuned large language models (LLMs) ranging in scale from 7 billion to 70 billion parameters.

14
Paper
Code

Habitat: A Platform for Embodied AI Research

facebookresearch/habitat-sim • • ICCV 2019

We present Habitat, a platform for research in embodied artificial intelligence (AI).

13
Paper
Code
Contact us on: hello@paperswithcode.com . Papers With Code is a free resource with all data licensed under CC-BY-SA.
Terms Data policy Cookies policy