Home Research Papers Datasets State of the Art Pricing

Discover, visualize, and connect AI research papers. Explore the latest trends and insights in artificial intelligence research.

Product

Home
Research Papers
About

Support

Contact
Terms of Service
Privacy Policy

© 2026 Papersgraph. All rights reserved.

computer-vision-5

Machine Reading Comprehension

3260 papers • 126 benchmarks • 313 datasets

Machine Reading Comprehension is one of the key problems in Natural Language Understanding, where the task is to read and comprehend a given text passage, and then answer questions based on it. Source: Making Neural Machine Reading Comprehension Faster

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in machine-reading-comprehension-5

Trend

Dataset

Best Model

Actions

ReClor

ReClor

DREAM

DREAM

UQuAD

UQuAD

Libraries

i

Use these libraries to find machine-reading-comprehension-5 models and implementations

alibaba/EasyNLP

2 papers 2,141

Datasets

LogiQA

MRQA

MCTest

CBT

ReClor

CMRC

Subtasks

No subtasks available.

Most implemented papers

MS MARCO: A Human Generated MAchine Reading COmprehension Dataset

L. Deng, Bhaskar Mitra, Daniel Fernando Campos, Jianfeng Gao, Tri Nguyen, Mir Rosenberg, Xia Song, Saurabh Tiwary, Rangan Majumder•Thu Nov 03 2016

This new dataset is aimed to overcome a number of well-known weaknesses of previous publicly available datasets for the same task of reading comprehension and question answering, and is the most comprehensive real-world dataset of its kind in both quantity and quality.

3179

Content

Introduction Benchmarks Datasets Subtasks Libraries Papers

BIOMRC

BIOMRC

2 papers 1,149

DREAM

DREAM

Belebele

MuTual

0

A Unified MRC Framework for Named Entity Recognition

Fei Wu, Yuxian Meng, Jiwei Li, Qinghong Han, Xiaoya Li, Jingrong Feng•Thu Oct 24 2019

This paper proposes to formulate the task of NER as a machine reading comprehension (MRC) task, and naturally tackles the entity overlapping issue in nested NER: the extraction of two overlapping entities with different categories requires answering two independent questions.

682 0

Stochastic Answer Networks for Machine Reading Comprehension

Jianfeng Gao, Yelong Shen, Kevin Duh, Xiaodong Liu•Sat Dec 09 2017

This work proposes a simple yet robust stochastic answer network (SAN) that simulates multi-step reasoning in machine reading comprehension that achieves results competitive to the state-of-the-art on the Stanford Question Answering Dataset, the Adversarial SQuAD, and the Microsoft MAchine Reading COmprehensionDataset.

203 0

SDNet: Contextualized Attention-based Deep Network for Conversational Question Answering

Xuedong Huang, Michael Zeng, Chenguang Zhu•Sun Dec 09 2018

An innovated contextualized attention-based deep neural network, SDNet, to fuse context into traditional MRC models, which leverages both inter-attention and self-att attention to comprehend conversation context and extract relevant information from passage.

131 0

Multi-task Learning with Sample Re-weighting for Machine Reading Comprehension

Jianfeng Gao, Yelong Shen, Jingjing Liu, Xiaodong Liu, Yichong Xu•Mon Sep 17 2018

A novel sample re-weighting scheme to assign sample-specific weights to the loss of a joint Machine Reading Comprehension (MRC) model that can be applied to a wide range of MRC tasks in different domains.

51 0

Stochastic Answer Networks for SQuAD 2.0

Jianfeng Gao, Kevin Duh, Aerin Kim, Yuwei Fang, Xiaodong Liu•Sun Sep 23 2018

An extension of the Stochastic Answer Network (SAN), one of the state-of-the-art machine reading comprehension models, to be able to judge whether a question is unanswerable or not, is presented.

24 0

Dice Loss for Data-imbalanced NLP Tasks

Yuxian Meng, Xiaofei Sun, Jiwei Li, Fei Wu, Xiaoya Li, Junjun Liang•Wed Nov 06 2019

This paper proposes to use dice loss in replacement of the standard cross-entropy objective for data-imbalanced NLP tasks, based on the Sørensen--Dice coefficient or Tversky index, which attaches similar importance to false positives and false negatives, and is more immune to the data-IMbalance issue.

694 0

KLUE: Korean Language Understanding Evaluation

Alice H. Oh, Sungjoon Park, Hyunwoo Kim, Jung-Woo Ha, Jihyung Moon, Won Ik Cho, Sungdong Kim, Kyunghyun Cho, Jiyoon Han, Jangwon Park, Chisung Song, Junseong Kim, Yongsook Song, Tae Hwan Oh, Joohong Lee, Juhyun Oh, Sungwon Lyu, Young-kuk Jeong, I. Lee, Sang-gyu Seo, Myeonghwa Lee, Seongbo Jang, Seungwon Do, SunKyoung Kim, Kyungtae Lim, Jongwon Lee, Kyumin Park, Jamin Shin, Seonghyun Kim, Lucy Park•Wed May 19 2021

This work introduces Korean Language Understanding Evaluation (KLUE), a collection of 8 Korean natural language understanding (NLU) tasks, including Topic Classification, SemanticTextual Similarity, Natural Language Inference, Named Entity Recognition, Relation Extraction, Dependency Parsing, Machine Reading Comprehension, and Dialogue State Tracking, and provides suitable evaluation metrics and fine-tuning recipes for pretrained language models for each task.

221 0

Reinforced Mnemonic Reader for Machine Reading Comprehension

M. Zhou, Furu Wei, Xipeng Qiu, Yuxing Peng, Minghao Hu, Zhen Huang•Sun May 07 2017

The Reinforced Mnemonic Reader for machine reading comprehension tasks, which enhances previous attentive readers in two aspects: a reattention mechanism is proposed to refine current attentions by directly accessing to past attentions that are temporally memorized in a multi-round alignment architecture.

216 0

DuReader: a Chinese Machine Reading Comprehension Dataset from Real-world Applications

Yizhong Wang, Wei He, Kai Liu, Jing Liu, Yajuan Lyu, Shiqi Zhao, Xinyan Xiao, Yuan Liu, Hua Wu, Qiaoqiao She, Xuan Liu, Tian Wu, Haifeng Wang•Mon Nov 13 2017

This paper introduces DuReader, a new large-scale, open-domain Chinese machine reading comprehension (MRC) dataset, designed to address real-world MRC, and organizes a shared competition to encourage the exploration of more models.

301 0

Adding a benchmark result helps the community track progress.

Machine Reading Comprehension | State-of-the-Art