SLING: A framework for frame semantic parsing
Computation and Language
2017-10-20 v1
Abstract
We describe SLING, a framework for parsing natural language into semantic frames. SLING supports general transition-based, neural-network parsing with bidirectional LSTM input encoding and a Transition Based Recurrent Unit (TBRU) for output decoding. The parsing model is trained end-to-end using only the text tokens as input. The transition system has been designed to output frame graphs directly without any intervening symbolic representation. The SLING framework includes an efficient and scalable frame store implementation as well as a neural network JIT compiler for fast inference during parsing. SLING is implemented in C++ and it is available for download on GitHub.
Cite
@article{arxiv.1710.07032,
title = {SLING: A framework for frame semantic parsing},
author = {Michael Ringgaard and Rahul Gupta and Fernando C. N. Pereira},
journal= {arXiv preprint arXiv:1710.07032},
year = {2017}
}