Implementation for the EMNLP 2021 paper "Interactive Machine Comprehension with Dynamic Knowledge Graphs".

Overview

Interactive Machine Comprehension with Dynamic Knowledge Graphs


Implementation for the EMNLP 2021 paper.

Dependencies

apt-get -y update
apt-get install -y unzip zip parallel
conda create -p /tmp/imrc python=3.6 numpy scipy cython nltk
conda activate /tmp/imrc
pip install --upgrade pip
pip install numpy==1.16.2
pip install gym==0.15.4
pip install tqdm pipreqs pyyaml pytz visdom
conda install pytorch torchvision cudatoolkit=9.2 -c pytorch
pip install transformers
pip install allennlp

Data Preparation

Split SQuAD 1.1 and preprocess

The original SQuAD dataset does not provide its test set, we take 23 wiki articles from its training set as our validation set. We then use the SQuAD dev set as our test set.

# download SQuAD from official website, then
python utils/split_original_squad.py

To speed up training, we parse (tokenization and SRL) the dataset in advance.

python utils/preproc_squad.py

This will result squad_split/processed_squad.1.1.split.[train/valid/test].json, which are used in iMRC tasks.

Preprocess Wikipedia data for self-supervised learning

python utils/get_wiki_filter_squad.py
python utils/split_wiki_data.py

This will result wiki_without_squad/wiki_without_squad_[train/valid/test].json, which are used to pre-train the continuous belief graph generator.

Training

To train the agent equipped with different types of graphs, run:

# without graph
python main.py configs/imrc_none.yaml

# co-occurrence graph
python main.py configs/imrc_cooccur.yaml

# relative position graph
python main.py configs/imrc_rel_pos.yaml

# SRL graph
python main.py configs/imrc_srl.yaml

# continuous belief graph
# in this setting, we need a pre-trained graph generator.
# we provide our pre-trained graph generator at
# https://drive.google.com/drive/folders/1zZ7C_-xaYsfg2Ms7_BO5n3Qzx69UqMKD?usp=sharing

# one can choose to train their own version by:
python pretrain_observation_infomax.py configs/pretrain_cont_bnelief.yaml
# then using the downloaded/saved model checkpoint
python main.py configs/imrc_cont_belief.yaml

To change the task settings/configurations:

general:
  naozi_capacity: 1  # capacity of agent's external memory queue (1, 3, 5)
  generate_or_point: "point"  # "qmpoint": q+o_t, "point": q, "generate": vocab
  disable_prev_next: False  # False: Easy Mode, True: Hard Mode

model:
  recurrent: True  # recurrent component described in Section 3.3 and Section 4.Additional Results

Citation

@inproceedings{Yuan2021imrc_graph,
  title={Interactive Machine Comprehension with Dynamic Knowledge Graphs},
  author={Xingdi Yuan},
  year={2021},
  booktitle="EMNLP",
}
Owner
Xingdi (Eric) Yuan
Senior Research Engineer at Microsoft Research, Montréal
Xingdi (Eric) Yuan
A knowledge base construction engine for richly formatted data

Fonduer is a Python package and framework for building knowledge base construction (KBC) applications from richly formatted data. Note that Fonduer is

HazyResearch 386 Dec 05, 2022
Deep Federated Learning for Autonomous Driving

FADNet: Deep Federated Learning for Autonomous Driving Abstract Autonomous driving is an active research topic in both academia and industry. However,

AIOZ AI 12 Dec 01, 2022
Generic Event Boundary Detection: A Benchmark for Event Segmentation

Generic Event Boundary Detection: A Benchmark for Event Segmentation We release our data annotation & baseline codes for detecting generic event bound

47 Nov 22, 2022
Graph Self-Attention Network for Learning Spatial-Temporal Interaction Representation in Autonomous Driving

GSAN Introduction Code for paper GSAN: Graph Self-Attention Network for Learning Spatial-Temporal Interaction Representation in Autonomous Driving, wh

YE Luyao 6 Oct 27, 2022
An abstraction layer for mathematical optimization solvers.

MathOptInterface Documentation Build Status Social An abstraction layer for mathematical optimization solvers. Replaces MathProgBase. Citing MathOptIn

JuMP-dev 284 Jan 04, 2023
Efficient 3D human pose estimation in video using 2D keypoint trajectories

3D human pose estimation in video with temporal convolutions and semi-supervised training This is the implementation of the approach described in the

Meta Research 3.1k Dec 29, 2022
The implemetation of Dynamic Nerual Garments proposed in Siggraph Asia 2021

DynamicNeuralGarments Introduction This repository contains the implemetation of Dynamic Nerual Garments proposed in Siggraph Asia 2021. ./GarmentMoti

42 Dec 27, 2022
CCNet: Criss-Cross Attention for Semantic Segmentation (TPAMI 2020 & ICCV 2019).

CCNet: Criss-Cross Attention for Semantic Segmentation Paper Links: Our most recent TPAMI version with improvements and extensions (Earlier ICCV versi

Zilong Huang 1.3k Dec 27, 2022
Cross-modal Retrieval using Transformer Encoder Reasoning Networks (TERN). With use of Metric Learning and FAISS for fast similarity search on GPU

Cross-modal Retrieval using Transformer Encoder Reasoning Networks This project reimplements the idea from "Transformer Reasoning Network for Image-Te

Minh-Khoi Pham 5 Nov 05, 2022
paper list in the area of reinforcenment learning for recommendation systems

paper list in the area of reinforcenment learning for recommendation systems

HenryZhao 23 Jun 09, 2022
An official source code for "Augmentation-Free Self-Supervised Learning on Graphs"

Augmentation-Free Self-Supervised Learning on Graphs An official source code for Augmentation-Free Self-Supervised Learning on Graphs paper, accepted

Namkyeong Lee 59 Dec 01, 2022
Official code for the paper: Deep Graph Matching under Quadratic Constraint (CVPR 2021)

QC-DGM This is the official PyTorch implementation and models for our CVPR 2021 paper: Deep Graph Matching under Quadratic Constraint. It also contain

Quankai Gao 55 Nov 14, 2022
Code for the paper "There is no Double-Descent in Random Forests"

Code for the paper "There is no Double-Descent in Random Forests" This repository contains the code to run the experiments for our paper called "There

2 Jan 14, 2022
Hierarchical Aggregation for 3D Instance Segmentation (ICCV 2021)

HAIS Hierarchical Aggregation for 3D Instance Segmentation (ICCV 2021) by Shaoyu Chen, Jiemin Fang, Qian Zhang, Wenyu Liu, Xinggang Wang*. (*) Corresp

Hust Visual Learning Team 145 Jan 05, 2023
A symbolic-model-guided fuzzer for TLS

tlspuffin TLS Protocol Under FuzzINg A symbolic-model-guided fuzzer for TLS Master Thesis | Thesis Presentation | Documentation Disclaimer: The term "

69 Dec 20, 2022
ICML 21 - Voice2Series: Reprogramming Acoustic Models for Time Series Classification

Voice2Series-Reprogramming Voice2Series: Reprogramming Acoustic Models for Time Series Classification International Conference on Machine Learning (IC

49 Jan 03, 2023
Speed-Test - You can check your intenet speed using this tool

Speed-Test Tool By Hez_X AVAILABLE ON : Termux & Kali linux & Ubuntu (Linux E

Hez-X 3 Feb 17, 2022
StrongSORT: Make DeepSORT Great Again

StrongSORT StrongSORT: Make DeepSORT Great Again StrongSORT: Make DeepSORT Great Again Yunhao Du, Yang Song, Bo Yang, Yanyun Zhao arxiv 2202.13514 Abs

369 Jan 04, 2023
A semantic segmentation toolbox based on PyTorch

Introduction vedaseg is an open source semantic segmentation toolbox based on PyTorch. Features Modular Design We decompose the semantic segmentation

407 Dec 15, 2022
Powerful and efficient Computer Vision Annotation Tool (CVAT)

Computer Vision Annotation Tool (CVAT) CVAT is free, online, interactive video and image annotation tool for computer vision. It is being used by our

OpenVINO Toolkit 8.6k Jan 01, 2023