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

arXiv: https://arxiv.org/abs/1706.09528 · HTML: https://mlsanity.com/paper/1706.09528/

## Key facts

- Cited by 33 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Jun 2017.

## Built on by (most cited first, 30 of 33)

- [Metaphor Generation with Conceptual Mappings](https://mlsanity.com/paper/2106.01228/) (2021)
- [Plot and Rework: Modeling Storylines for Visual Storytelling](https://mlsanity.com/paper/2105.06950/) (2021)
- [A Double-Graph Based Framework for Frame Semantic Parsing](https://mlsanity.com/paper/2206.09158/) (2022)
- [DiffusEmp: A Diffusion Model-Based Framework with Multi-Grained Control for Empathetic Response Generation](https://mlsanity.com/paper/2306.01657/) (2023)
- [Coarse-to-Fine Dual Encoders are Better Frame Identification Learners](https://mlsanity.com/paper/2310.13316/) (2023)
- [A Graph-Based Neural Model for End-to-End Frame Semantic Parsing](https://mlsanity.com/paper/2109.12319/) (2021)
- [Understanding Narratives through Dimensions of Analogy](https://mlsanity.com/paper/2206.07167/) (2022)
- [Automatic extraction of materials and properties from superconductors scientific literature](https://mlsanity.com/paper/2210.15600/) (2022)
- [Joint Universal Syntactic and Semantic Parsing](https://mlsanity.com/paper/2104.05696/) (2021)
- [Semantic Role Labeling Meets Definition Modeling: Using Natural Language to Describe Predicate-Argument Structures](https://mlsanity.com/paper/2212.01094/) (2022)
- [Semantic Frame Forecast](https://mlsanity.com/paper/2104.05604/) (2021)
- [Knowledge Authoring with Factual English](https://mlsanity.com/paper/2208.03094/) (2022)
- [Open-source Frame Semantic Parsing](https://mlsanity.com/paper/2303.12788/) (2023)
- [Can LLMs Extract Frame-Semantic Arguments?](https://mlsanity.com/paper/2502.12516/) (2025)
- [Do LLMs Encode Frame Semantics? Evidence from Frame Identification](https://mlsanity.com/paper/2509.19540/) (2025)
- [Sister Help: Data Augmentation for Frame-Semantic Role Labeling](https://mlsanity.com/paper/2109.07725/) (2021)
- [Domain Adaptation in Neural Machine Translation using a Qualia-Enriched FrameNet](https://mlsanity.com/paper/2202.10287/) (2022)
- [Query Your Model with Definitions in FrameNet: An Effective Method for Frame Semantic Role Labeling](https://mlsanity.com/paper/2212.02036/) (2022)
- [Knowledge Authoring for Rules and Actions](https://mlsanity.com/paper/2305.07763/) (2023)
- [Annotating FrameNet via Structure-Conditioned Language Generation](https://mlsanity.com/paper/2406.04834/) (2024)
- [Not all ANIMALs are equal: metaphorical framing through source domains and semantic frames](https://mlsanity.com/paper/2604.20454/) (2026)
- [Knowledge-augmented Frame Semantic Parsing with Hybrid Prompt-tuning](https://mlsanity.com/paper/2303.14375/) (2023)
- [Semantic Frame Induction with Deep Metric Learning](https://mlsanity.com/paper/2304.14286/) (2023)
- [Knowledge Authoring with Factual English, Rules, and Actions](https://mlsanity.com/paper/2411.06253/) (2024)
- [Beyond the Battlefield: Framing Analysis of Media Coverage in Conflict Reporting](https://mlsanity.com/paper/2506.10421/) (2025)
- [Kicktionary-LOME: A Domain-Specific Multilingual Frame Semantic Parsing Model for Football Language](https://mlsanity.com/paper/2108.05575/) (2021)
- [Ranking Facts for Explaining Answers to Elementary Science Questions](https://mlsanity.com/paper/2110.09036/) (2021)
- [Let's Talk! Striking Up Conversations via Conversational Visual Question Generation](https://mlsanity.com/paper/2205.09327/) (2022)
- [EventNet-ITA: Italian Frame Parsing for Events](https://mlsanity.com/paper/2305.10892/) (2023)
- [Evaluating the Ability of Computationally Extracted Narrative Maps to Encode Media Framing](https://mlsanity.com/paper/2405.02677/) (2024)

## Abstract (arXiv)

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.