This code is part of the reproducibility package for the SANER 2022 paper "Generating Clarifying Questions for Query Refinement in Source Code Search".

Related tags

Deep LearningZaCQ
Overview

Clarifying Questions for Query Refinement in Source Code Search

This code is part of the reproducibility package for the SANER 2022 paper "Generating Clarifying Questions for Query Refinement in Source Code Search".

It consists of five folders:

  • codesearch/ - API to access the CodeSearchNet datasets and neural bag-of-words code retrieval method.

  • cq/ - Implementation of the ZaCQ system, including an implementation of the the TaskNav development task extraction algorithm and two baseline query refinement methods.

  • data/ - Includes pretrained code search model and config files for task extraction.

  • evaluation/ - Scripts to run and evaluate ZaCQ.

  • interface/ - Backend and Frontend servers for a search interface implementing ZaCQ.

Setup

  1. Clone the CodeSearchNet package to the root directory, and download the CSN datasets
cd ZaCQ
git clone https://github.com/github/CodeSearchNet.git
cd CodeSearchNet/scripts
./download_and_preprocess
  1. Use a CSN model to create vector representations for candidate code search results. A pretrained Neural BoW model is included in this package.
cd codesearch
python -m venv venv
source venv/bin/activate
pip install -r requirements.txt
python _setup.py

This will save and index vectors in the data folder. It will also generate search results for the 99 CSN queries.

  1. Task extraction is fairly quick for small sets of code search results, but it is expensive to do repeatedly. To expedite the evaluation, we cache the extracted tasks for the results of the 99 CSN queries, as well as keywords for all functions in the datasets.
cd cq
python -m venv venv
source venv/bin/activate
pip install -r requirements.txt
python _setup.py

Cached tasks and keywords are stored in the data folder.

Evaluation

To evaluate the ZaCQ and the other query refinement methods on the CSN queries, you may use the following:

cd evaluation
python run_queries.py
python evaluate.py

The run_queries script determines the subset of CSN queries that can be automatically evaluated, and simulates interactive refinement sessions for all valid questions for each language in CSN. For ZaCQ, the script runs through a set of predefined hyperparameter combinations. The script calculates NDCG, MAP, and MRE metrics for each refinement method and hyperparameter configuration, and stores them in the data/output folder

The evaluate script averages the metrics across all languages after 1-N rounds of refinement. For ZaCQ, it also records the best-performing hyperparamter combination after n rounds of refinement.

Interface

To run the interactive search interface, you need to run two backend servers and start the GUI server:

cd interface/cqserver
python ClarifyAPI.py
cd interface/searchserver
python SearchAPI.py
cd interface/gui
npm start

By default, you can access the GUI at localhost:3000

Owner
Zachary Eberhart
Zachary Eberhart
Source code for "Understanding Knowledge Integration in Language Models with Graph Convolutions"

Graph Convolution Simulator (GCS) Source code for "Understanding Knowledge Integration in Language Models with Graph Convolutions" Requirements: PyTor

yifan 10 Oct 18, 2022
Semi-supervised Domain Adaptation via Minimax Entropy

Semi-supervised Domain Adaptation via Minimax Entropy (ICCV 2019) Install pip install -r requirements.txt The code is written for Pytorch 0.4.0, but s

Vision and Learning Group 243 Jan 09, 2023
Official Implementation for Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation

Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation We present a generic image-to-image translation framework, pixel2style2pixel (pSp

2.8k Dec 30, 2022
[ICCV 2021] Target Adaptive Context Aggregation for Video Scene Graph Generation

Target Adaptive Context Aggregation for Video Scene Graph Generation This is a PyTorch implementation for Target Adaptive Context Aggregation for Vide

Multimedia Computing Group, Nanjing University 44 Dec 14, 2022
SOLOv2 on onnx & tensorRT

SOLOv2.tensorRT: NOTE: code based on WXinlong/SOLO add support to TensorRT inference onnxruntime tensorRT full_dims and dynamic shape postprocess with

47 Nov 26, 2022
One Million Scenes for Autonomous Driving

ONCE Benchmark This is a reproduced benchmark for 3D object detection on the ONCE (One Million Scenes) dataset. The code is mainly based on OpenPCDet.

148 Dec 28, 2022
CVPR 2021 Official Pytorch Code for UC2: Universal Cross-lingual Cross-modal Vision-and-Language Pre-training

UC2 UC2: Universal Cross-lingual Cross-modal Vision-and-Language Pre-training Mingyang Zhou, Luowei Zhou, Shuohang Wang, Yu Cheng, Linjie Li, Zhou Yu,

Mingyang Zhou 28 Dec 30, 2022
Unleashing Transformers: Parallel Token Prediction with Discrete Absorbing Diffusion for Fast High-Resolution Image Generation from Vector-Quantized Codes

Unleashing Transformers: Parallel Token Prediction with Discrete Absorbing Diffusion for Fast High-Resolution Image Generation from Vector-Quantized C

Sam Bond-Taylor 139 Jan 04, 2023
Pytorch implementation for our ICCV 2021 paper "TRAR: Routing the Attention Spans in Transformers for Visual Question Answering".

TRAnsformer Routing Networks (TRAR) This is an official implementation for ICCV 2021 paper "TRAR: Routing the Attention Spans in Transformers for Visu

Ren Tianhe 49 Nov 10, 2022
Py-faster-rcnn - Faster R-CNN (Python implementation)

py-faster-rcnn has been deprecated. Please see Detectron, which includes an implementation of Mask R-CNN. Disclaimer The official Faster R-CNN code (w

Ross Girshick 7.8k Jan 03, 2023
The code release of paper Low-Light Image Enhancement with Normalizing Flow

[AAAI 2022] Low-Light Image Enhancement with Normalizing Flow Paper | Project Page Low-Light Image Enhancement with Normalizing Flow Yufei Wang, Renji

Yufei Wang 176 Jan 06, 2023
Federated learning on graph, especially on graph neural networks (GNNs), knowledge graph, and private GNN.

Federated learning on graph, especially on graph neural networks (GNNs), knowledge graph, and private GNN.

keven 198 Dec 20, 2022
Official code of our work, AVATAR: A Parallel Corpus for Java-Python Program Translation.

AVATAR Official code of our work, AVATAR: A Parallel Corpus for Java-Python Program Translation. AVATAR stands for jAVA-pyThon progrAm tRanslation. AV

Wasi Ahmad 26 Dec 03, 2022
[ECE NTUA] 👁 Computer Vision - Lab Projects & Theoretical Problem Sets (2020-2021)

Computer Vision - NTUA (2020-2021) This repository hosts the lab projects and theoretical problem sets of the Computer Vision course held by ECE NTUA

Dimitris Dimos 6 Jul 21, 2022
Dynamic Visual Reasoning by Learning Differentiable Physics Models from Video and Language (NeurIPS 2021)

VRDP (NeurIPS 2021) Dynamic Visual Reasoning by Learning Differentiable Physics Models from Video and Language Mingyu Ding, Zhenfang Chen, Tao Du, Pin

Mingyu Ding 36 Sep 20, 2022
STEAL - Learning Semantic Boundaries from Noisy Annotations (CVPR 2019)

STEAL This is the official inference code for: Devil Is in the Edges: Learning Semantic Boundaries from Noisy Annotations David Acuna, Amlan Kar, Sanj

469 Dec 26, 2022
OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation

Build Type Linux MacOS Windows Build Status OpenPose has represented the first real-time multi-person system to jointly detect human body, hand, facia

25.7k Jan 09, 2023
PyTorch implementation of Graph Convolutional Networks in Feature Space for Image Deblurring and Super-resolution, IJCNN 2021.

GCResNet PyTorch implementation of Graph Convolutional Networks in Feature Space for Image Deblurring and Super-resolution, IJCNN 2021. The code will

11 May 19, 2022
[CVPR-2021] UnrealPerson: An adaptive pipeline for costless person re-identification

UnrealPerson: An Adaptive Pipeline for Costless Person Re-identification In our paper (arxiv), we propose a novel pipeline, UnrealPerson, that decreas

ZhangTianyu 70 Oct 10, 2022
YOLOv5 Series Multi-backbone, Pruning and quantization Compression Tool Box.

YOLOv5-Compression Update News Requirements 环境安装 pip install -r requirements.txt Evaluation metric Visdrone Model mAP ZhangYuan 719 Jan 02, 2023