Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.
Awesome Lists | Featured Topics | Projects
https://github.com/NTMC-Community/MatchZoo-py

Facilitating the design, comparison and sharing of deep text matching models.
https://github.com/NTMC-Community/MatchZoo-py
deep-learning matching natural-language-processing neural-network pytorch text text-matching
Last synced: about 2 months ago
JSON representation
Facilitating the design, comparison and sharing of deep text matching models.
Host: GitHub
URL: https://github.com/NTMC-Community/MatchZoo-py
Owner: NTMC-Community
License: apache-2.0
Created: 2019-06-17T14:15:36.000Z (over 5 years ago)
Default Branch: master
Last Pushed: 2024-05-03T19:50:11.000Z (5 months ago)
Last Synced: 2024-07-25T21:56:17.269Z (about 2 months ago)
Topics: deep-learning, matching, natural-language-processing, neural-network, pytorch, text, text-matching
Language: Python
Homepage:
Size: 598 KB
Stars: 496
Watchers: 21
Forks: 106
Open Issues: 29
Metadata Files:
- Readme: README.md
- Contributing: CONTRIBUTING.md
- License: LICENSE
- Codeowners: CODEOWNERS
Awesome Lists containing this project

awesome-semantic-search - matchzoo-py
StarryDivineSky - NTMC-Community/MatchZoo-py
README

        






# MatchZoo-py [![Tweet](https://img.shields.io/twitter/url/http/shields.io.svg?style=social)](https://twitter.com/intent/tweet?text=MatchZoo-py:%20deep%20learning%20for%20semantic%20matching&url=https://github.com/NTMC-Community/MatchZoo-py)

> PyTorch version of [MatchZoo](https://github.com/NTMC-Community/MatchZoo).

> Facilitating the design, comparison and sharing of deep text matching models.


> MatchZoo 是一个通用的文本匹配工具包，它旨在方便大家快速的实现、比较、以及分享最新的深度文本匹配模型。

[![Python 3.6](https://img.shields.io/badge/python-3.6%20%7C%203.7-blue.svg)](https://www.python.org/downloads/release/python-360/)

[![Pypi Downloads](https://img.shields.io/pypi/dm/matchzoo-py.svg?label=pypi)](https://pypi.org/project/MatchZoo-py/)

[![Documentation Status](https://readthedocs.org/projects/matchzoo-py/badge/?version=latest)](https://matchzoo-py.readthedocs.io/en/latest/?badge=latest)

[![Build Status](https://travis-ci.org/NTMC-Community/MatchZoo-py.svg?branch=master)](https://travis-ci.org/NTMC-Community/MatchZoo-py)

[![codecov](https://codecov.io/gh/NTMC-Community/MatchZoo-py/branch/master/graph/badge.svg)](https://codecov.io/gh/NTMC-Community/MatchZoo-py)

[![License](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)

[![Requirements Status](https://requires.io/github/NTMC-Community/MatchZoo-py/requirements.svg?branch=master)](https://requires.io/github/NTMC-Community/MatchZoo-py/requirements/?branch=master)

[![Gitter](https://badges.gitter.im/NTMC-Community/community.svg)](https://gitter.im/NTMC-Community/community?utm_source=badge&utm_medium=badge&utm_campaign=pr-badge)

---

The goal of MatchZoo is to provide a high-quality codebase for deep text matching research, such as document retrieval, question answering, conversational response ranking, and paraphrase identification. With the unified data processing pipeline, simplified model configuration and automatic hyper-parameters tunning features equipped, MatchZoo is flexible and easy to use.

  

    Tasks 

    Text 1

    Text 2

    Objective

  

  

     Paraphrase Indentification 

     string 1 

     string 2 

     classification 

  

  

     Textual Entailment 

     text 

     hypothesis 

     classification 

  

  

     Question Answer 

     question 

     answer 

     classification/ranking 

  

  

     Conversation 

     dialog 

     response 

     classification/ranking 

  

  

     Information Retrieval 

     query 

     document 

     ranking 

  

## Get Started in 60 Seconds

To train a [Deep Semantic Structured Model](https://www.microsoft.com/en-us/research/project/dssm/), make use of MatchZoo customized loss functions and evaluation metrics to define a task:

```python

import torch

import matchzoo as mz

ranking_task = mz.tasks.Ranking(losses=mz.losses.RankCrossEntropyLoss(num_neg=4))

ranking_task.metrics = [

    mz.metrics.NormalizedDiscountedCumulativeGain(k=3),

    mz.metrics.MeanAveragePrecision()

]

```

Prepare input data:

```python

train_pack = mz.datasets.wiki_qa.load_data('train', task=ranking_task)

valid_pack = mz.datasets.wiki_qa.load_data('dev', task=ranking_task)

```

Preprocess your input data in three lines of code, keep track parameters to be passed into the model:

```python

preprocessor = mz.models.ArcI.get_default_preprocessor()

train_processed = preprocessor.fit_transform(train_pack)

valid_processed = preprocessor.transform(valid_pack)

```

Generate pair-wise training data on-the-fly:

```python

trainset = mz.dataloader.Dataset(

    data_pack=train_processed,

    mode='pair',

    num_dup=1,

    num_neg=4,

    batch_size=32

)

validset = mz.dataloader.Dataset(

    data_pack=valid_processed,

    mode='point',

    batch_size=32

)

```

Define padding callback and generate data loader:

```python

padding_callback = mz.models.ArcI.get_default_padding_callback()

trainloader = mz.dataloader.DataLoader(

    dataset=trainset,

    stage='train',

    callback=padding_callback

)

validloader = mz.dataloader.DataLoader(

    dataset=validset,

    stage='dev',

    callback=padding_callback

)

```

Initialize the model, fine-tune the hyper-parameters:

```python

model = mz.models.ArcI()

model.params['task'] = ranking_task

model.params['embedding_output_dim'] = 100

model.params['embedding_input_dim'] = preprocessor.context['embedding_input_dim']

model.guess_and_fill_missing_params()

model.build()

```

`Trainer` is used to control the training flow:

```python

optimizer = torch.optim.Adam(model.parameters())

trainer = mz.trainers.Trainer(

    model=model,

    optimizer=optimizer,

    trainloader=trainloader,

    validloader=validloader,

    epochs=10

)

trainer.run()

```

## References

[Tutorials](https://github.com/NTMC-Community/MatchZoo-py/tree/master/tutorials)

[English Documentation](https://matchzoo-py.readthedocs.io/en/latest/)

If you're interested in the cutting-edge research progress, please take a look at [awaresome neural models for semantic match](https://github.com/NTMC-Community/awaresome-neural-models-for-semantic-match).

## Install

MatchZoo-py is dependent on [PyTorch](https://pytorch.org). Two ways to install MatchZoo-py:

**Install MatchZoo-py from Pypi:**

```python

pip install matchzoo-py

```

**Install MatchZoo-py from the Github source:**

```

git clone https://github.com/NTMC-Community/MatchZoo-py.git

cd MatchZoo-py

python setup.py install

```

## Models

- [DRMM](https://github.com/NTMC-Community/MatchZoo-py/tree/master/matchzoo/models/drmm.py): this model is an implementation of A Deep Relevance Matching Model for Ad-hoc Retrieval.

- [DRMMTKS](https://github.com/NTMC-Community/MatchZoo-py/tree/master/matchzoo/models/drmmtks.py): this model is an implementation of A Deep Top-K Relevance Matching Model for Ad-hoc Retrieval.

- [ARC-I](https://github.com/NTMC-Community/MatchZoo-py/tree/master/matchzoo/models/arci.py): this model is an implementation of Convolutional Neural Network Architectures for Matching Natural Language Sentences

- [ARC-II](https://github.com/NTMC-Community/MatchZoo-py/tree/master/matchzoo/models/arcii.py): this model is an implementation of Convolutional Neural Network Architectures for Matching Natural Language Sentences

- [DSSM](https://github.com/NTMC-Community/MatchZoo-py/tree/master/matchzoo/models/dssm.py): this model is an implementation of Learning Deep Structured Semantic Models for Web Search using Clickthrough Data

- [CDSSM](https://github.com/NTMC-Community/MatchZoo-py/tree/master/matchzoo/models/cdssm.py): this model is an implementation of Learning Semantic Representations Using Convolutional Neural Networks for Web Search

- [MatchLSTM](https://github.com/NTMC-Community/MatchZoo-py/tree/master/matchzoo/models/matchlstm.py):this model is an implementation of Machine Comprehension Using Match-LSTM and Answer Pointer

- [DUET](https://github.com/NTMC-Community/MatchZoo-py/tree/master/matchzoo/models/duet.py): this model is an implementation of Learning to Match Using Local and Distributed Representations of Text for Web Search

- [KNRM](https://github.com/NTMC-Community/MatchZoo-py/tree/master/matchzoo/models/knrm.py): this model is an implementation of End-to-End Neural Ad-hoc Ranking with Kernel Pooling

- [ConvKNRM](https://github.com/NTMC-Community/MatchZoo-py/tree/master/matchzoo/models/conv_knrm.py): this model is an implementation of Convolutional neural networks for soft-matching n-grams in ad-hoc search

- [ESIM](https://github.com/NTMC-Community/MatchZoo-py/tree/master/matchzoo/models/esim.py): this model is an implementation of Enhanced LSTM for Natural Language Inference

- [BiMPM](https://github.com/NTMC-Community/MatchZoo-py/tree/master/matchzoo/models/bimpm.py): this model is an implementation of Bilateral Multi-Perspective Matching for Natural Language Sentences

- [MatchPyramid](https://github.com/NTMC-Community/MatchZoo-py/tree/master/matchzoo/models/match_pyramid.py): this model is an implementation of Text Matching as Image Recognition

- [Match-SRNN](https://github.com/NTMC-Community/MatchZoo-py/tree/master/matchzoo/models/match_srnn.py): this model is an implementation of Match-SRNN: Modeling the Recursive Matching Structure with Spatial RNN

- [aNMM](https://github.com/NTMC-Community/MatchZoo-py/tree/master/matchzoo/models/anmm.py): this model is an implementation of aNMM: Ranking Short Answer Texts with Attention-Based Neural Matching Model

- [MV-LSTM](https://github.com/NTMC-Community/MatchZoo-py/tree/master/matchzoo/models/mvlstm.py): this model is an implementation of A Deep Architecture for Semantic Matching with Multiple Positional Sentence Representations

- [DIIN](https://github.com/NTMC-Community/MatchZoo-py/tree/master/matchzoo/models/diin.py): this model is an implementation of Natural Lanuguage Inference Over Interaction Space

- [HBMP](https://github.com/NTMC-Community/MatchZoo-py/tree/master/matchzoo/models/hbmp.py): this model is an implementation of Sentence Embeddings in NLI with Iterative Refinement Encoders

- [BERT](https://github.com/NTMC-Community/MatchZoo-py/tree/master/matchzoo/models/bert.py): this model is an implementation of BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

## Citation

If you use MatchZoo in your research, please use the following BibTex entry.

```

@inproceedings{Guo:2019:MLP:3331184.3331403,

 author = {Guo, Jiafeng and Fan, Yixing and Ji, Xiang and Cheng, Xueqi},

 title = {MatchZoo: A Learning, Practicing, and Developing System for Neural Text Matching},

 booktitle = {Proceedings of the 42Nd International ACM SIGIR Conference on Research and Development in Information Retrieval},

 series = {SIGIR'19},

 year = {2019},

 isbn = {978-1-4503-6172-9},

 location = {Paris, France},

 pages = {1297--1300},

 numpages = {4},

 url = {http://doi.acm.org/10.1145/3331184.3331403},

 doi = {10.1145/3331184.3331403},

 acmid = {3331403},

 publisher = {ACM},

 address = {New York, NY, USA},

 keywords = {matchzoo, neural network, text matching},

} 

```

## Development Team

    

  

    

      

         


         Yixing Fan 

        
Core Dev


        ASST PROF, ICT

      

      

         


         Jiangui Chen 

        Core Dev
 PhD. ICT

      

      

         


         Yinqiong Cai

         Core Dev
 M.S. ICT

      

      

         


         Liang Pang 

        Core Dev


        ASST PROF, ICT

      

      

         


         Lixin Su

        Dev


        PhD. ICT

      

    

    

      

         


         Ruibin Xiong 

        Dev


        M.S. ICT

      

      

         


         Yuyang Ding 

        Dev


        M.S. ICT

      

      

         


         Junfeng Tian 

        Dev


        M.S. ECNU

      

      

         


         Qinghua Wang 

        Documentation


        B.S. Shandong Univ.

      

    

  

## Contribution

Please make sure to read the [Contributing Guide](./CONTRIBUTING.md) before creating a pull request. If you have a MatchZoo-related paper/project/compnent/tool, send a pull request to [this awesome list](https://github.com/NTMC-Community/awaresome-neural-models-for-semantic-match)!

Thank you to all the people who already contributed to MatchZoo!

[Bo Wang](https://github.com/bwanglzu), [Zeyi Wang](https://github.com/uduse), [Liu Yang](https://github.com/yangliuy), [Zizhen Wang](https://github.com/ZizhenWang), [Zhou Yang](https://github.com/zhouzhouyang520), [Jianpeng Hou](https://github.com/HouJP), [Lijuan Chen](https://github.com/githubclj), [Yukun Zheng](https://github.com/zhengyk11), [Niuguo Cheng](https://github.com/niuox), [Dai Zhuyun](https://github.com/AdeDZY), [Aneesh Joshi](https://github.com/aneesh-joshi), [Zeno Gantner](https://github.com/zenogantner), [Kai Huang](https://github.com/hkvision), [stanpcf](https://github.com/stanpcf), [ChangQF](https://github.com/ChangQF), [Mike Kellogg

](https://github.com/wordreference)

## Project Organizers

- Jiafeng Guo

  * Institute of Computing Technology, Chinese Academy of Sciences

  * [Homepage](http://www.bigdatalab.ac.cn/~gjf/)

- Yanyan Lan

  * Institute of Computing Technology, Chinese Academy of Sciences

  * [Homepage](http://www.bigdatalab.ac.cn/~lanyanyan/)

- Xueqi Cheng

  * Institute of Computing Technology, Chinese Academy of Sciences

  * [Homepage](http://www.bigdatalab.ac.cn/~cxq/)

## License

[Apache-2.0](https://opensource.org/licenses/Apache-2.0)

Copyright (c) 2019-present, Yixing Fan (faneshion)