# Unsupervised Induction of Semantic Roles within a Reconstruction-Error Minimization Framework

arXiv: https://arxiv.org/abs/1412.2812 · HTML: https://mlsanity.com/paper/1412.2812/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Dec 2014.

## Built on by (most cited first, 3 of 3)

- [Weakly Supervised Text Classification using Supervision Signals from a Language Model](https://mlsanity.com/paper/2205.06604/) (2022)
- [Potential and Limitations of LLMs in Capturing Structured Semantics: A Case Study on SRL](https://mlsanity.com/paper/2405.06410/) (2024)
- [Neural Unsupervised Semantic Role Labeling](https://mlsanity.com/paper/2104.09047/) (2021)

## Abstract (arXiv)

We introduce a new approach to unsupervised estimation of feature-rich semantic role labeling models. Our model consists of two components: (1) an encoding component: a semantic role labeling model which predicts roles given a rich set of syntactic and lexical features; (2) a reconstruction component: a tensor factorization model which relies on roles to predict argument fillers. When the components are estimated jointly to minimize errors in argument reconstruction, the induced roles largely correspond to roles defined in annotated resources. Our method performs on par with most accurate role induction methods on English and German, even though, unlike these previous approaches, we do not incorporate any prior linguistic knowledge about the languages.