Frame-Semantic Parsing with Softmax-Margin Segmental RNNs and a Syntactic Scaffold
2017-06-29Code Available1· sign in to hype
Swabha Swayamdipta, Sam Thomson, Chris Dyer, Noah A. Smith
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/Noahs-ARK/open-sesameOfficialIn papernone★ 0
- github.com/chanind/frame-semantic-transformernone★ 65
- github.com/tyjiangu/fidopytorch★ 3
- github.com/swabhs/open-sesamenone★ 0
- github.com/danielfoster15/mlt_thesis_open_sesamenone★ 0
- github.com/clingergab/srnone★ 0
- github.com/gsatallion8/Framenet-Frame-Parsernone★ 0
- github.com/Asteur/Frame-semantic-SegRNNnone★ 0
- github.com/MartinoMensio/open-sesame-APInone★ 0
- github.com/swabhs/coling18tutorialnone★ 0
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.