A Chinese to English Neural Model Translation Project

Overview

ZH-EN NMT Chinese to English Neural Machine Translation

This project is inspired by Stanford's CS224N NMT Project

Dataset used in this project: News Commentary v14

Intro

This project is more of a learning project to make myself familiar with Pytorch, machine translation, and NLP model training.

To investigate how would various setups of the recurrent layer affect the final performance, I compared Training Efficiency and Effectiveness of different types of RNN layer for encoder by changing one feature each time while controlling all other parameters:

  • RNN types

    • GRU
    • LSTM
  • Activation Functions on Output Layer

    • Tanh
    • ReLU
    • LeakyReLU
  • Number of layers

    • single layer
    • double layer

Code Files

_/
├─ utils.py # utilities
├─ vocab.py # generate vocab
├─ model_embeddings.py # embedding layer
├─ nmt_model.py # nmt model definition
├─ run.py # training and testing

Good Translation Examples

  • source: 相反,这意味着合作的基础应当是共同的长期战略利益,而不是共同的价值观。

    • target: Instead, it means that cooperation must be anchored not in shared values, but in shared long-term strategic interests.
    • translation: On the contrary, that means cooperation should be a common long-term strategic interests, rather than shared values.
  • source: 但这个问题其实很简单: 谁来承受这些用以降低预算赤字的紧缩措施的冲击。

    • target: But the issue is actually simple: Who will bear the brunt of measures to reduce the budget deficit?
    • translation: But the question is simple: Who is to bear the impact of austerity measures to reduce budget deficits?
  • source: 上述合作对打击恐怖主义、贩卖人口和移民可能发挥至关重要的作用。

    • target: Such cooperation is essential to combat terrorism, human trafficking, and migration.
    • translation: Such cooperation is essential to fighting terrorism, trafficking, and migration.
  • source: 与此同时, 政治危机妨碍着政府追求艰难的改革。

    • target: At the same time, political crisis is impeding the government’s pursuit of difficult reforms.
    • translation: Meanwhile, political crises hamper the government’s pursuit of difficult reforms.

Preprocessing

Preprocessing Colab notebook

  • using jieba to separate Chinese words by spaces

Generate Vocab From Training Data

  • Input: training data of Chinese and English

  • Output: a vocab file containing mapping from (sub)words to ids of Chinese and English -- a limited size of vocab is selected using SentencePiece (essentially Byte Pair Encoding of character n-grams) to cover around 99.95% of training data

Model Definition

  • a Seq2Seq model with attention

    This image is from the book DIVE INTO DEEP LEARNING

    • Encoder
      • A Recurrent Layer
    • Decoder
      • LSTMCell (hidden_size=512)
    • Attention
      • Multiplicative Attention

Training And Testing Results

Training Colab notebook

  • Hyperparameters:
    • Embedding Size & Hidden Size: 512
    • Dropout Rate: 0.25
    • Starting Learning Rate: 5e-4
    • Batch Size: 32
    • Beam Size for Beam Search: 10
  • NOTE: The BLEU score calculated here is based on the Test Set, so it could only be used to compare the relative effectiveness of the models using this data

For Experiment

  • Dataset: the dataset is split into training set(~260000), validation set(~20000), and testing set(~20000) randomly (they are the same for each experiment group)
  • Max Number of Iterations: 50000
  • NOTE: I've tried Vanilla-RNN(nn.RNN) in various ways, but the BLEU score turns out to be extremely low for it (absence of residual connections might be the issue)
    • I decided to not include it for comparison until the issue is resolved
Training Time(sec) BLEU Score on Test Set Training Perplexities Validation Perplexities
A. Bidirectional 1-Layer GRU with Tanh 5158.99 14.26
B. Bidirectional 1-Layer LSTM with Tanh 5150.31 16.20
C. Bidirectional 2-Layer LSTM with Tanh 6197.58 16.38
D. Bidirectional 1-Layer LSTM with ReLU 5275.12 14.01
E. Bidirectional 1-Layer LSTM with LeakyReLU(slope=0.1) 5292.58 14.87

Current Best Version

Bidirectional 2-Layer LSTM with Tanh, 1024 embed_size & hidden_size, trained 11517.19 sec (44000 iterations), BLEU score 17.95

Traning Time BLEU Score on Test Set Training Perplexities Validation Perplexities
Best Model 11517.19 17.95

Analysis

  • LSTM tends to have better performance than GRU (it has an extra set of parameters)
  • Tanh tends to be better since less information is lost
  • Making the LSTM deeper (more layers) could improve the performance, but it cost more time to train
  • Surprisingly, the training time for A, B, and D are roughly the same
    • the issue may be the dataset is not large enough, or the cloud service I used to train models does not perform consistently

Bad Examples & Case Analysis

  • source: 全球目击组织(Global Witness)的报告记录, 光是2015年就有16个国家的185人被杀。
    • target: A Global Witness report documented 185 killings across 16 countries in 2015 alone.
    • translation: According to the Global eye, the World Health Organization reported that 185 people were killed in 2015.
    • problems:
      • Information Loss: 16 countries
      • Unknown Proper Noun: Global Witness
  • source: 大自然给了足以满足每个人需要的东西, 但无法满足每个人的贪婪
    • target: Nature provides enough for everyone’s needs, but not for everyone’s greed.
    • translation: Nature provides enough to satisfy everyone.
    • problems:
      • Huge Information Loss
  • source: 我衷心希望全球经济危机和巴拉克·奥巴马当选总统能对新冷战的荒唐理念进行正确的评估。
    • target: It is my hope that the global economic crisis and Barack Obama’s presidency will put the farcical idea of a new Cold War into proper perspective.
    • translation: I do hope that the global economic crisis and President Barack Obama will be corrected for a new Cold War.
    • problems:
      • Action Sender And Receiver Exchanged
      • Failed To Translate Complex Sentence
  • source: 人们纷纷猜测欧元区将崩溃。
    • target: Speculation about a possible breakup was widespread.
    • translation: The eurozone would collapse.
    • problems:
      • Significant Information Loss

Means to Improve the NMT model

  • Dataset
    • The dataset is fairly small, and our model is not being trained thorough all data
    • Being a native Chinese speaker, I could not understand what some of the source sentences are saying
    • The target sentences are not informational comprehensive; they themselves need context to be understood (e.g. the target sentence in the last "Bad Examples")
    • Even for human, some of the source sentence was too hard to translate
  • Model Architecture
    • CNN & Transformer
    • character based model
    • Make the model even larger & deeper (... I need GPUs)
  • Tricks that might help
    • Add a proper noun dictionary to translate unknown proper nouns word-by-word (phrase-by-phrase)
    • Initialize (sub)word embedding with pretrained embedding

How To Run

  • Download the dataset you desire, and change all "./zh_en_data" in run.sh to the path where your data is stored
  • To run locally on a CPU (mostly for sanity check, CPU is not able to train the model)
    • set up the environment using conda/miniconda conda env create --file local env.yml
  • To run on a GPU
    • set up the environment and running process following the Colab notebook

Contact

If you have any questions or you have trouble running the code, feel free to contact me via email

Owner
Zhenbang Feng
Be an engineer, not a coder. [email protected]
Zhenbang Feng
Various Algorithms for Short Text Mining

Short Text Mining in Python Introduction This package shorttext is a Python package that facilitates supervised and unsupervised learning for short te

Kwan-Yuet 466 Dec 06, 2022
A collection of Korean Text Datasets ready to use using Tensorflow-Datasets.

tfds-korean A collection of Korean Text Datasets ready to use using Tensorflow-Datasets. TensorFlow-Datasets를 이용한 한국어/한글 데이터셋 모음입니다. Dataset Catalog |

Jeong Ukjae 20 Jul 11, 2022
Samantha, A covid-19 information bot which will provide basic information about this pandemic in form of conversation.

Covid-19-BOT Samantha, A covid-19 information bot which will provide basic information about this pandemic in form of conversation. This bot uses torc

Neeraj Majhi 2 Nov 05, 2021
: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
Python port of Google's libphonenumber

phonenumbers Python Library This is a Python port of Google's libphonenumber library It supports Python 2.5-2.7 and Python 3.x (in the same codebase,

David Drysdale 3.1k Dec 29, 2022
Abhijith Neil Abraham 2 Nov 05, 2021
An A-SOUL Text Generator Based on CPM-Distill.

ASOUL-Generator-Backend 本项目为 https://asoul.infedg.xyz/ 的后端。 模型为基于 CPM-Distill 的 transformers 转化版本 CPM-Generate-distill 训练而成。

infinityedge 46 Dec 11, 2022
Ukrainian TTS (text-to-speech) using Coqui TTS

title emoji colorFrom colorTo sdk app_file pinned Ukrainian TTS 🐸 green green gradio app.py false Ukrainian TTS 📢 🤖 Ukrainian TTS (text-to-speech)

Yurii Paniv 85 Dec 26, 2022
This repository describes our reproducible framework for assessing self-supervised representation learning from speech

LeBenchmark: a reproducible framework for assessing SSL from speech Self-Supervised Learning (SSL) using huge unlabeled data has been successfully exp

49 Aug 24, 2022
End-to-End Speech Processing Toolkit

ESPnet: end-to-end speech processing toolkit system/pytorch ver. 1.0.1 1.1.0 1.2.0 1.3.1 1.4.0 1.5.1 1.6.0 1.7.1 1.8.1 ubuntu18/python3.8/pip ubuntu18

ESPnet 5.9k Jan 03, 2023
Neural Lexicon Reader: Reduce Pronunciation Errors in End-to-end TTS by Leveraging External Textual Knowledge

Neural Lexicon Reader: Reduce Pronunciation Errors in End-to-end TTS by Leveraging External Textual Knowledge This is an implementation of the paper,

Mutian He 19 Oct 14, 2022
a chinese segment base on crf

Genius Genius是一个开源的python中文分词组件,采用 CRF(Conditional Random Field)条件随机场算法。 Feature 支持python2.x、python3.x以及pypy2.x。 支持简单的pinyin分词 支持用户自定义break 支持用户自定义合并词

duanhongyi 237 Nov 04, 2022
Code for EMNLP 2021 main conference paper "Text AutoAugment: Learning Compositional Augmentation Policy for Text Classification"

Code for EMNLP 2021 main conference paper "Text AutoAugment: Learning Compositional Augmentation Policy for Text Classification"

LancoPKU 105 Jan 03, 2023
: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
Anomaly Detection 이상치 탐지 전처리 모듈

Anomaly Detection 시계열 데이터에 대한 이상치 탐지 1. Kernel Density Estimation을 활용한 이상치 탐지 train_data_path와 test_data_path에 존재하는 시점 정보를 포함하고 있는 csv 형태의 train data와

CLUST-consortium 43 Nov 28, 2022
"Investigating the Limitations of Transformers with Simple Arithmetic Tasks", 2021

transformers-arithmetic This repository contains the code to reproduce the experiments from the paper: Nogueira, Jiang, Lin "Investigating the Limitat

Castorini 33 Nov 16, 2022
Python module (C extension and plain python) implementing Aho-Corasick algorithm

pyahocorasick pyahocorasick is a fast and memory efficient library for exact or approximate multi-pattern string search meaning that you can find mult

Wojciech Muła 763 Dec 27, 2022
Wikipedia-Utils: Preprocessing Wikipedia Texts for NLP

Wikipedia-Utils: Preprocessing Wikipedia Texts for NLP This repository maintains some utility scripts for retrieving and preprocessing Wikipedia text

Masatoshi Suzuki 44 Oct 19, 2022
Google's Meena transformer chatbot implementation

Here's my attempt at recreating Meena, a state of the art chatbot developed by Google Research and described in the paper Towards a Human-like Open-Domain Chatbot.

Francesco Pham 94 Dec 25, 2022
Paddlespeech Streaming ASR GUI

Paddlespeech-Streaming-ASR-GUI Introduction A paddlespeech Streaming ASR GUI. Us

Niek Zhen 3 Jan 05, 2022