i-Parser: Interactive Parser Development Kit for Natural Language Processing

Authors

  • Gaku Morio Research and Development Group, Hitachi, Ltd.
  • Hiroaki Ozaki Research and Development Group, Hitachi, Ltd.
  • Yuta Koreeda Research and Development Group, Hitachi America, Ltd.
  • Terufumi Morishita Research and Development Group, Hitachi, Ltd.
  • Toshinori Miyoshi Research and Development Group, Hitachi, Ltd.

DOI:

https://doi.org/10.1609/aaai.v35i18.18021

Keywords:

Dependency Parsing, Visualization, Syntax, Semantic Parsing, Interactive System

Abstract

This demonstration paper presents i-Parser, a novel development kit that produces high-performance semantic parsers. i-Parser converts training graphs into sequences written in a context-free language, then our proposed model learns to generate the sequences. With interactive configuration and visualization, users can easily build their own parsers. Benchmark results of i-Parser showed high performances of various parsing tasks in natural language processing.

Downloads

Published

2021-05-18

How to Cite

Morio, G., Ozaki, H., Koreeda, Y., Morishita, T., & Miyoshi, T. (2021). i-Parser: Interactive Parser Development Kit for Natural Language Processing. Proceedings of the AAAI Conference on Artificial Intelligence, 35(18), 16091-16093. https://doi.org/10.1609/aaai.v35i18.18021