# Frame-Semantic Parsing with Softmax-Margin Segmental RNNs and a Syntactic Scaffold

Source: [Frame-Semantic Parsing with Softmax-Margin Segmental RNNs and a Syntactic Scaffold](<https://www.sota2.com/research/paper/68fa63711e209131ce9fee0b>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T20:41:16.530Z

Authors: Swabha Swayamdipta, Sam Thomson, Chris Dyer, Noah A. Smith

Published: 2017-06-29T00:42:10.000Z

## Abstract

We present a new, efficient frame-semantic parser that labels semantic arguments to FrameNet predicates. Built using an extension to the segmental RNN that emphasizes recall, our basic system achieves competitive performance without any calls to a syntactic parser. We then introduce a method that uses phrase-syntactic annotations from the Penn Treebank during training only, through a multitask objective; no parsing is required at training or test time. This "syntactic scaffold" offers a cheaper alternative to traditional syntactic pipelining, and achieves state-of-the-art performance.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Semantic Role Classification on FrameNet 1.7 (test)](<https://www.sota2.com/research/sota/semantic-role-classification-on-framenet-1-7-test.md>): Semantic Role Classification; FrameNet 1.7 (test); Accuracy: 58.46.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1706.09528>)

[PDF](<https://arxiv.org/pdf/1706.09528.pdf>)
