Jie Gao

RESOURCES

Credbank pre-trained ELMo model for rumour tweets representation learning, available via [figshare shef.data.11591775.v1]

Sooji Han, Jie Gao, & Fabio Ciravegna. (2019). Augmented dataset of rumours and non-rumours for rumour detection v1.0 [Data set]. Zenodo. http://doi.org/10.5281/zenodo.3249977

Gao J. (2017), jgtextrank 0.1.1: Yet another Python implementation of TextRank: package for the creation, manipulation, and study of TextRank algorithm based keywords extraction and summarisation. Available via [link]

Zhang, z., Gao, J., (2016). JATE - Java Automatic Term Extraction library, Latest release on May 24th, 2017. Available via [link]

Source code of JATE 2.0 live demo presented LREC 2016 conference is also available via [link]. Please See also the page

SPEEAK-PC Terminology Recognition (SPTR) implements an Automatic Terminology Recognition (ATR) and automatic indexing tool providing the integration with Apache Solr using Nature Language Processing technology. The source code is available via [link]

Source code of oke-challenge Task 2(2015): Class Induction and entity typing for Vocabulary and Knowledge Base enrichment is available via [link]

A deprecated Sensor Data Collection server providing HTTP/HTTPS RESTful web services previously used in our MoveMore and WeSenseIt Project is open-sourced via the [link]. The server is implemented based on Java Platform, Enterprise Edition (JEE) including Spring Framework + Hibernate for ORM + Apache CXF + JBOSS RESTEasy + Swagger for API Documentation. There are project-specific sensor data models and RESTful APIs, spatial data clustering methods, data processing(e.g., support extract ctx/gpx activity data), etc, which are possibly still useful for related requirements. You can also check my notes for our previous practices in terms of Encrypted Access, HTTP/HTTPS configuration for compressed data request, optimisation for large data streams, etc.