We present SetExpander, a corpus-based system for expanding a seed set of terms into amore complete set of terms that belong to the same semantic class. SetExpander implements an iterative end-to-end workflow. It enables users to easily select a seed set of terms, expand it, view the expanded set, validate it, re-expand the validated set and store it, thus simplifying the extraction of domain-specific fine-grained semantic classes.SetExpander has been used successfully in real-life use cases including integration into an automated recruitment system and an issues and defects resolution system. A video demo of SetExpander is available at https://drive.google.com/open?id=1e545bB87Autsch36DjnJHmq3HWfSd1Rv (some images were blurred for privacy reasons)
@article{arxiv.1808.08953,
title = {Term Set Expansion based NLP Architect by Intel AI Lab},
author = {Jonathan Mamou and Oren Pereg and Moshe Wasserblat and Alon Eirew and Yael Green and Shira Guskin and Peter Izsak and Daniel Korat},
journal= {arXiv preprint arXiv:1808.08953},
year = {2018}
}
Comments
EMNLP 2018 System Demonstrations. arXiv admin note: substantial text overlap with arXiv:1807.10104