NL. The natural language programming language.

Related tags

Text Data & NLPNL
Overview

NL

A Natural-Language programming language. Built using Codex.

A few examples are inside the nl_projects directory.

How it works

Write any code in pure english, and have it compiled and run as regular code would. The only rules are:

  • Must have the .nl file extension
  • Every command is separated by a line-break
  • Make sure to keep the number of stuff per-line to a minimum. Doing so will result in better compilation.
  • comments are put in-between parentheses

Example: Guessing game.

Compiling a guessing game program looks something like this:

First you write the code in NL:

(the following is a guessing game)
create a maximum number of 100

Repeat forever...
Store a number between 1 and the maximum number. Call it the answer.
Increase the maximum number by 20
Tell the user that you are thinking of a number between 0 and the maximum number. Tell the user that they only have 14 chances to get it right.
Repeat 14 times...
Ask the user for a guess, and Convert it to a number
if the guess is equal to the answer, congrad the user and end the loop.
otherwise if the guess is higher or lower than the answer, tell the user.
Tell the user how many chances are left.
when the loop has ended, if the user has not guessed the answer, tell the user game over and then exit the game

When you compile the code, it gets copied into a directory and auto-indented (This stage can be skipped if desired, but doing so will result in greater likelyhood of erroneous code.):

Create a maximum number of 100

Repeat forever...
    Store a number between 1 and the maximum number. Call it the answer.
    Increase the maximum number by 20.
    Tell the user that you are thinking of a number between 0 and the maximum number. Tell the user that they only have 14 chances to get it right.
    Repeat 14 times...
        Ask the user for a guess, and Convert it to a number
        If the guess is equal to the answer, congradulate the user and end the loop.
        Otherwise if the guess is higher or lower than the answer, tell the user.
        Tell the user how many chances are left.
    When loop has ended, If user has not guessed the answer, tell the user game over and then exit the game.

Which then gets compiled to python code and executed:

answer: print("Your guess is too high") else: print("Your guess is too low") # CMD: Tell the user how many chances are left. print("You have " + str(14 - i) + " chances left") # CMD: When loop has ended, If user has not guessed the answer, tell the user game over and then exit the game. if guess != answer: print("Game over") exit()">
import random

# CMD: Create a maximum number of 100
max = 100
# CMD: Repeat forever...
while True:
    # CMD: Store a number between 1 and the maximum number. Call it the answer.
    answer = random.randint(1,max)
    # CMD: Increase the maximum number by 20.
    max = max + 20
    # CMD: Tell the user that you are thinking of a number between 0 and the maximum number. Tell the user that they only have 14 chances to get it right.
    print("I am thinking of a number between 0 and " + str(max))
    # CMD: Repeat 14 times...
    for i in range(0,14):
        # CMD: Ask the user for a guess, and Convert it to a number
        guess = int(input("Guess a number:"))
        # CMD: If the guess is equal to the answer, congradulate the user and end the loop.
        if guess == answer:
            print("You guessed it!")
            break;
        # CMD: Otherwise if the guess is higher or lower than the answer, tell the user.
        elif guess > answer:
            print("Your guess is too high")
        else: 
            print("Your guess is too low")
        # CMD: Tell the user how many chances are left.
        print("You have " + str(14 - i) + " chances left")
    # CMD: When loop has ended, If user has not guessed the answer, tell the user game over and then exit the game.
    if guess != answer:
        print("Game over")
        exit()

API List of commands (in compilation.py)

  • compile(nl_code_path)
  • compileAndRun(nl_code_path)
  • run(python_code_path)
  • compileWithoutCorrection(nl_code_path) Compiles without creating an indentation file to compile.
Quantifiers and Negations in RE Documents

Quantifiers-and-Negations-in-RE-Documents This project was part of my work for a

Nicolas Ruscher 1 Feb 01, 2022
EMNLP'2021: Can Language Models be Biomedical Knowledge Bases?

BioLAMA BioLAMA is biomedical factual knowledge triples for probing biomedical LMs. The triples are collected and pre-processed from three sources: CT

DMIS Laboratory - Korea University 41 Nov 18, 2022
Code for lyric-section-to-comment generation based on huggingface transformers.

CommentGeneration Code for lyric-section-to-comment generation based on huggingface transformers. Migrate Guyu model and code (both 12-layers and 24-l

Yawei Sun 8 Sep 04, 2021
BiQE: Code and dataset for the BiQE paper

BiQE: Bidirectional Query Embedding This repository includes code for BiQE and the datasets introduced in Answering Complex Queries in Knowledge Graph

Bhushan Kotnis 1 Oct 20, 2021
Code for evaluating Japanese pretrained models provided by NTT Ltd.

japanese-dialog-transformers 日本語の説明文はこちら This repository provides the information necessary to evaluate the Japanese Transformer Encoder-decoder dialo

NTT Communication Science Laboratories 216 Dec 22, 2022
Top2Vec is an algorithm for topic modeling and semantic search.

Top2Vec is an algorithm for topic modeling and semantic search. It automatically detects topics present in text and generates jointly embedded topic, document and word vectors.

Dimo Angelov 2.4k Jan 06, 2023
GAP-text2SQL: Learning Contextual Representations for Semantic Parsing with Generation-Augmented Pre-Training

GAP-text2SQL: Learning Contextual Representations for Semantic Parsing with Generation-Augmented Pre-Training Code and model from our AAAI 2021 paper

Amazon Web Services - Labs 83 Jan 09, 2023
:hot_pepper: R²SQL: "Dynamic Hybrid Relation Network for Cross-Domain Context-Dependent Semantic Parsing." (AAAI 2021)

R²SQL The PyTorch implementation of paper Dynamic Hybrid Relation Network for Cross-Domain Context-Dependent Semantic Parsing. (AAAI 2021) Requirement

huybery 60 Dec 31, 2022
This is the Alpha of Nutte language, she is not complete yet / Essa é a Alpha da Nutte language, não está completa ainda

nutte-language This is the Alpha of Nutte language, it is not complete yet / Essa é a Alpha da Nutte language, não está completa ainda My language was

catdochrome 2 Dec 18, 2021
PyKaldi is a Python scripting layer for the Kaldi speech recognition toolkit.

PyKaldi is a Python scripting layer for the Kaldi speech recognition toolkit. It provides easy-to-use, low-overhead, first-class Python wrappers for t

922 Dec 31, 2022
Live Speech Portraits: Real-Time Photorealistic Talking-Head Animation (SIGGRAPH Asia 2021)

Live Speech Portraits: Real-Time Photorealistic Talking-Head Animation This repository contains the implementation of the following paper: Live Speech

OldSix 575 Dec 31, 2022
Black for Python docstrings and reStructuredText (rst).

Style-Doc Style-Doc is Black for Python docstrings and reStructuredText (rst). It can be used to format docstrings (Google docstring format) in Python

Telekom Open Source Software 13 Oct 24, 2022
Line as a Visual Sentence: Context-aware Line Descriptor for Visual Localization

Line as a Visual Sentence with LineTR This repository contains the inference code, pretrained model, and demo scripts of the following paper. It suppo

SungHo Yoon 158 Dec 27, 2022
End-to-end image captioning with EfficientNet-b3 + LSTM with Attention

Image captioning End-to-end image captioning with EfficientNet-b3 + LSTM with Attention Model is seq2seq model. In the encoder pretrained EfficientNet

2 Feb 10, 2022
This is a project of data parallel that running on NLP tasks.

This is a project of data parallel that running on NLP tasks.

2 Dec 12, 2021
[WWW 2021 GLB] New Benchmarks for Learning on Non-Homophilous Graphs

New Benchmarks for Learning on Non-Homophilous Graphs Here are the codes and datasets accompanying the paper: New Benchmarks for Learning on Non-Homop

94 Dec 21, 2022
NumPy String-Indexed is a NumPy extension that allows arrays to be indexed using descriptive string labels

NumPy String-Indexed NumPy String-Indexed is a NumPy extension that allows arrays to be indexed using descriptive string labels, rather than conventio

Aitan Grossman 1 Jan 08, 2022
:mag: Transformers at scale for question answering & neural search. Using NLP via a modular Retriever-Reader-Pipeline. Supporting DPR, Elasticsearch, HuggingFace's Modelhub...

Haystack is an end-to-end framework that enables you to build powerful and production-ready pipelines for different search use cases. Whether you want

deepset 6.4k Jan 09, 2023
This is the source code of RPG (Reward-Randomized Policy Gradient)

RPG (Reward-Randomized Policy Gradient) Zhenggang Tang*, Chao Yu*, Boyuan Chen, Huazhe Xu, Xiaolong Wang, Fei Fang, Simon Shaolei Du, Yu Wang, Yi Wu (

40 Nov 25, 2022
A repo for open resources & information for people to succeed in PhD in CS & career in AI / NLP

A repo for open resources & information for people to succeed in PhD in CS & career in AI / NLP

420 Dec 28, 2022