operation-prediction

KO | EN

gitlite — search

#sql #svg #claude #gpt #machine-learning #self-hosted #nodejs #proxy #data-science #generative-ai

operation-prediction

(★ 12)

Takes a question predicts the operation between them

파일 탐색기

ZIP 다운로드

- addsub.json
- ans.txt
- eq.txt
- q.txt
- singleop.json
- test_LSTM_26112016
- train_LSTM_26112016
- basic steps
- find_operands_in_question.py
- main.py
- model_json_GRU_21112017_tensorflow_pre_padding_0.5dropout.json
- my_model.h5
- mynewmodel.h5
- parameters_GRU_21112017_tensorflow_pre_padding_0.5dropout
- predict_operation_and_operands_to_find_answer.py
- question_to_answer.txt
- test.txt
- tested_questions.txt
- train.txt
- train_and_predict_operation.sh
- train_model_for_operation_prediction.py
- weights_GRU_21112017_tensorflow_pre_padding_0.5dropout
- Comparison.png
- DifferentModelsAccuracy.png
- word_problem.png
- model.py
- standardmodel.py
- test_aris.py
.gitignore
model1.py
README.md
relevant_quantities.py
requirements.txt

# CDN으로 사용하기

jsDelivr

jsDelivr는 공개 GitHub 리포지토리를 별도 설정 없이 CDN으로 즉시 서빙합니다. 버전과 파일을 고르면 웹페이지에 바로 붙일 수 있는 링크와 예시 코드가 만들어집니다.

버전

파일

링크

예시

# 프로젝트 배지

Word Probem

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

This is the code for the paper http://www.aclweb.org/anthology/I17-3017

Blog link https://medium.com/@purvanshimehta/can-computers-learn-maths-through-deep-learning-7ef714ca2cb3

Takes a question with two operands as input and predicts the operation between them. This system presents a novel approach to
solve simple arithmetic word problems.We predict the operation that is to be performed (’-’,’+’,’*’,’/’) through a deep neu-
ral network model and then use it to generate the answer.

The question is divided into two parts - worldstate and query as shown in Figure .

The worldstate and the query are processed separately in two different networks and finally the networks
are merged to predict the final operation.

Our system learns to predict operationswith 88.81 % in a corpus of primary school questions.

### Prerequisites

pip install -r requirements.txt

## Getting Started

1) Testing on our data

python3 model.py DATA/train_LSTM_26112016 DATA/test_LSTM_26112016

2) ### Web
run
python3 model1.py

The function main_function returns the answer

API code is in main.py

3) Testing on ARIS

python3 test_aris.py

## Results and Comparisions

![Result](https://raw.githubusercontent.com/purvanshi/operation-prediction/master/images/DifferentModelsAccuracy.png)
![Baselines](https://raw.githubusercontent.com/purvanshi/operation-prediction/master/images/Comparison.png)

## Testing

You can change the input question 
eg - 
1) Joan found 70 seashells on the beach . she gave Sam some of her seashells . She has 27 seashell . How many seashells did she give to Sam ?

2) There were 28 bales of hay in the barn . Tim stacked bales in the barn today . There are now 54 bales of hay in the barn . How many bales did he store in the barn ? 
3) Mary is baking a cake . The recipe wants 8 cups of flour . She already put in 2 cups . How many cups does she need to add ? 
4) Sara 's high school played 12 basketball games this year . The team won most of their games . They were defeated during 4 games . How many games did they win ?

operation-prediction

오너의 다른 레포

파일 탐색기

# CDN으로 사용하기

# 프로젝트 배지

Was this content helpful?

Recent Feedback

operation-prediction

오너의 다른 레포

파일 탐색기

# CDN으로 사용하기

# 프로젝트 배지

Was this content helpful?

Recent Feedback

Download README