SLING: A framework for frame semantic parsing

TL;DR

SLING is a neural-network-based framework for direct semantic frame parsing from text, featuring an end-to-end transition system, efficient implementation, and scalable frame storage.

Contribution

It introduces a novel transition-based neural parsing approach for semantic frames that outputs frame graphs directly without symbolic intermediates.

Findings

Supports real-time parsing with fast inference.

Achieves accurate semantic frame parsing from raw text.

Provides scalable and efficient implementation.

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.