Giter Site home page Giter Site logo

Hi, I'm Noe Casas. I specialize in natural language processing (NLP) and artificial intelligence (AI).

If you're a startup/company looking for guidance in your endeavours, feel free to reach out at [email protected]. I'd be happy to discuss how I can be of assistance to you. Check out my LinkedIn profile or the summary below to know the areas where I could be helpful.

如果您是家需要技术指导和支持的公司,请通过 [email protected] 联系我来安排咨询服务(汉语、英语都可以)。我们能讨论怎么合作。立刻查看我的领英资料或下面的摘要来了解我可以提供帮助的领域。

Areas of expertise:

  • Machine translation, language modelling and NLP: I hold a PhD in Neural Machine Translation and have been doing NLP (deep learning-based and classical) for the last 5 years, both in Python and C++; I also have experience in speech processing and computer vision. I do both Pytorch and Tensorflow/Keras. Lately, I have been doing integrations with GPT-3.5 and GPT-4.
  • Data science: experience with the Python stack: scikit-learn, pandas, etc. I deal with SQL every day. Regarding algorithms: experience with logistic regression, SVMs, linear regression, Bayesian linear models, A/B testing, gradient-boosted trees, k-means, hdbscan.
  • Software development: almost 20 years of professional programming experience. Extensive backend experience in Python, Javascript, C++, and Java; experience also in mobile development in Kotlin and Swift, and some web development with React.
  • Systems engineering: experience building scalable internet-facing services based on node.js/python, nginx, redis and SQL databases.

By the way, I am currently creating a language learning app for both teachers and students called Langtern. Find out more at www.langtern.com


Profiles:

Noe Casas's Projects

cfilt_preorder icon cfilt_preorder

Rule based source reordering system for English-Indian language translation

chinese-cloze-rc icon chinese-cloze-rc

A Chinese Cloze-style RC Dataset: People's Daily & Children's Fairy Tale (CFT)

cmrc2019 icon cmrc2019

A Sentence Cloze Dataset for Chinese Machine Reading Comprehension (CMRC 2019)

coco-cn icon coco-cn

Enriching MS-COCO with Chinese sentences and tags for cross-lingual multimedia tasks

compmt icon compmt

Compositional Machine Translation

differentiable-bleu icon differentiable-bleu

Source code of article A differentiable BLEU loss. Analysis and first results (https://openreview.net/forum?id=HkG7hzyvf)

drcd icon drcd

A 30000+ Chinese MRC dataset - Delta Reading Comprehension Dataset

dress-data icon dress-data

Data for the DRESS simplification model (EMNLP 2017) described in http://aclweb.org/anthology/D/D17/D17-1062.pdf

encoding icon encoding

Header-only C++11 library to encode pieces of data with tight control over their bit-level representation.

fairseq icon fairseq

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

frugally-deep icon frugally-deep

Header-only library for using Keras (TensorFlow) models in C++.

gcrc icon gcrc

This work focuses on multiple-choice questions in Gaokao Chinese. A highly challenging multiple-choice MRC task is from the Chinese University Admission Examination (Gaokao in Chinese), which called GCRC as follows.Unlike its counterparts which rely on numerical reasoning and specialized field knowledge, GCRC focuses on testing language comprehension. All of the questions in this dataset are answerable without any other knowledge.

gene icon gene

Simple genetic algorithms library in C++11

gtpbridge icon gtpbridge

Go Text Protocol bridging layer to allow massive interoperability of different Go engines

gtplib icon gtplib

Header-only C++11 implementation of the Go Text Protocol (GTP)

hanzi_lookup icon hanzi_lookup

Free, open-source, browser-based Chinese handwriting recognition in Rust / Web Assembly

hsk30 icon hsk30

HSK 3.0 Vocabulary Lists (words and characters)

hugo-academic icon hugo-academic

The website designer for Hugo. Build and deploy a beautiful website in minutes :rocket:

mtp icon mtp

Multi-lingual Text Processing

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.