A PyTorch implementation of Neural Ranker-Reader model for Machine Reading Comprehension

Решение, занимающее 28/184 место в отборочном контесте ONTI "AI" на датасете MuSeRC.

CS Bachelor Thesis. Open Domain Question Answering System that tries to answer general topic questions fetching from wikipedia.

Endeavour to make full use of hierarchical information to extract span from product reviews for user questions

A solutions for https://onti2020.ai-academy.ru by @otter18

Contextualized commonsense knowledge

a new large-scale challenging dataset for CLRC (Cross-Lingual Reading Comprehension)

Machine Reading Comprehension over Forest Rights Act

Linguistic-knowledge-aware Neuro-symbolic Model for Entity State Tracking

Build a Question&Answering System with Deep Learning.

Domain adaptation in open domain question answering is tackled through theme specific rankers. We also propose a novel resource allocation algorithm to select the number of paragraph to be examined for extracting the answering. Finished 1st among participating IITs in Inter IIT tech Meet 11.0

Cooking Recipe MRC using PEFT techniques

Machine Comprehension on Squad Dataset using Match-LSTM + Ans-Ptr Network

ExamQA

Answers your questions

This repo includes the data and code for the demo paper titled "Climate Bot: A Machine Reading Comprehension System for Climate Change Question Answering"

Reasoning Shortcuts in MRC

An Open-Source Toolkit for Machine Reading Comprehension and Textual Question Answering Based on PyTorch. 基于PyTorch的机器阅读理解与文本问答开源工具