GluonNLP: An Easy-to-Use Deep Learning for NLP Toolkit
GluonNLP is a toolkit that enables easy text preprocessing, datasets loading and neural models building to help speed up the process of producing the state-of-the-art NLP research.
- I am a co-creator of GluonNLP.
- Github: github.com/dmlc/gluon-nlp
- Website: gluon-nlp.mxnet.io
- Published in KDD 2019.
- Submitted to ACL 2020 and JMLR.
AutoGluon: An AutoML Toolkit for Deep Learning
AutoGluon enables easy-to-use AutoML with a focus on deep learning and real-world applications in text, image, or tabular data.
TextHIN: A Text-to-Network Representation and Semantic Parsing Toolkit
TextHIN converts unstructured text into structured networks and produces the state-of-the-art results on several text mining problems mainly including text classification, text clustering, text similarity search.
- I am the creator of TextHIN.
- Github: github.com/cgraywang/TextHIN
- Data: github.com/cgraywang/TextHINData
- Published in DMKD 2018, CIKM 2017, TKDD 2016, AAAI 2016, ICDM 2015, and KDD 2015.
SystemT: A Declarative Information Extraction System
SystemT aims to extract structured information from unstructured or semi-structured data. It makes information extraction orders of magnitude more scalable and easy to use, maintain and customize.
- I am a contributor of SystemT.
- Demo: https://researcher.watson.ibm.com/researcher/view_group_subpage.php?id=6342
- Published in IJCAI 2017 and EMNLP 2017.
UniversalPropositions: Universal Proposition Banks for Multilingual Semantic Role Labeling
UniversalPropositions aims to annotate text in different languages with a layer of “universal” semantic role labeling annotation.
- I am a contributor of UniversalPropositions.
- Github: github.com/System-T/UniversalPropositions
- Demo: Multilingual Semantic Role Labeling
- Filed a U.S. patent.
D2L.ai: Dive into Deep Learning
An interactive deep learning book with code, math, and discussions.
Apache MXNet: Efficient and Flexible Deep Learning
One of the major deep learning frameworks.