# Learning Joint Semantic Parsers from Disjoint Data

arXiv: https://arxiv.org/abs/1804.05990 · HTML: https://mlsanity.com/paper/1804.05990/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Apr 2018.

## Built on by (most cited first, 12 of 12)

- [LOME: Large Ontology Multilingual Extraction](https://mlsanity.com/paper/2101.12175/) (2021)
- [FinReport: Explainable Stock Earnings Forecasting via News Factor Analyzing Model](https://mlsanity.com/paper/2403.02647/) (2024)
- [A Double-Graph Based Framework for Frame Semantic Parsing](https://mlsanity.com/paper/2206.09158/) (2022)
- [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)
- [Semantic Role Labeling Meets Definition Modeling: Using Natural Language to Describe Predicate-Argument Structures](https://mlsanity.com/paper/2212.01094/) (2022)
- [Open-source Frame Semantic Parsing](https://mlsanity.com/paper/2303.12788/) (2023)
- [Do LLMs Encode Frame Semantics? Evidence from Frame Identification](https://mlsanity.com/paper/2509.19540/) (2025)
- [Query Your Model with Definitions in FrameNet: An Effective Method for Frame Semantic Role Labeling](https://mlsanity.com/paper/2212.02036/) (2022)
- [Annotating FrameNet via Structure-Conditioned Language Generation](https://mlsanity.com/paper/2406.04834/) (2024)
- [Frame Shift Prediction](https://mlsanity.com/paper/2201.01837/) (2022)
- [Task Decomposition for Efficient Annotation](https://mlsanity.com/paper/2606.24734/) (2026)

## Abstract (arXiv)

We present a new approach to learning semantic parsers from multiple datasets, even when the target semantic formalisms are drastically different, and the underlying corpora do not overlap. We handle such "disjoint" data by treating annotations for unobserved formalisms as latent structured variables. Building on state-of-the-art baselines, we show improvements both in frame-semantic parsing and semantic dependency parsing by modeling them jointly.