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

Swabha Swayamdipta, Sam Thomson, Chris Dyer, Noah A. Smith
6/29/2017
cs.CL

Official code: swabhs/open-sesame (244 stars, Apache-2.0, last commit 2022-05-07).

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.

View on arXivView PDF

Code Implementations(1)

swabhs/open-sesameOfficial100%
Apache-2.0

A frame-semantic parsing system based on a softmax-margin SegRNN.

24468PythonJun 16, 20174 years agoApache-2.0
crfdeep-learningdynetframe-semantic-parsingnatural-language-processing+2 more

Similar Papers

Widely Interpretable Semantic Representation: Frameless Meaning Representation for Broader Applicability

83% match2023

Knowledge-augmented Frame Semantic Parsing with Hybrid Prompt-tuning

80% match2023

Learning Joint Semantic Parsers from Disjoint Data

80% match1 repo712018

Semantic Operator Prediction and Applications

79% match2023

Holistic Exploration on Universal Decompositional Semantic Parsing: Architecture, Data Augmentation, and LLM Paradigm

78% match1 repo42023

CAIT: A Syntactic Parsing Toolkit for Child-Adult InTeractions

78% match2026

Cite this paper

@article{swayamdipta2017framesemantic,
  title  = {Frame-Semantic Parsing with Softmax-Margin Segmental RNNs and a Syntactic Scaffold},
  author = {Swabha Swayamdipta and Sam Thomson and Chris Dyer and Noah A. Smith},
  year   = {2017},
  eprint = {1706.09528},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1706.09528}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1706.09528.svg)](https://codeofpaper.com/paper/1706.09528)

Discussion