Question Answering

1088 papers with code • 64 benchmarks • 249 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 ( Image credit: SQuAD )

Greatest papers with code

Big Bird: Transformers for Longer Sequences

tensorflow/models NeurIPS 2020

To remedy this, we propose, BigBird, a sparse attention mechanism that reduces this quadratic dependency to linear.

 Ranked #1 on Question Answering on Natural Questions (F1 (Long) metric)

Linguistic Acceptability Natural Language Inference +3

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

tensorflow/models 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.

Language Modelling Natural Language Understanding +2

Learning a Natural Language Interface with Neural Programmer

tensorflow/models 28 Nov 2016

The main experimental result in this paper is that a single Neural Programmer model achieves 34. 2% accuracy using only 10, 000 examples with weak supervision.

Program induction Question Answering

Predicting Subjective Features of Questions of QA Websites using BERT

tensorflow/models ICWR 2020

Community Question-Answering websites, such as StackOverflow and Quora, expect users to follow specific guidelines in order to maintain content quality.

Community Question Answering

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

tensorflow/models NAACL 2019

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

Common Sense Reasoning Conversational Response Selection +6

Talking-Heads Attention

tensorflow/models 5 Mar 2020

We introduce "talking-heads attention" - a variation on multi-head attention which includes linearprojections across the attention-heads dimension, immediately before and after the softmax operation. While inserting only a small number of additional parameters and a moderate amount of additionalcomputation, talking-heads attention leads to better perplexities on masked language modeling tasks, aswell as better quality when transfer-learning to language comprehension and question answering tasks.

Language Modelling Question Answering +1

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

tensorflow/models ICLR 2020

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

Common Sense Reasoning Linguistic Acceptability +4

Fine-tune the Entire RAG Architecture (including DPR retriever) for Question-Answering

huggingface/transformers 22 Jun 2021

In this paper, we illustrate how to fine-tune the entire Retrieval Augment Generation (RAG) architecture in an end-to-end manner.

Open-Domain Question Answering

mT5: A massively multilingual pre-trained text-to-text transformer

huggingface/transformers NAACL 2021

The recent "Text-to-Text Transfer Transformer" (T5) leveraged a unified text-to-text format and scale to attain state-of-the-art results on a wide variety of English-language NLP tasks.

Common Sense Reasoning Natural Language Inference +2