# Unsupervised Transfer of Semantic Role Models from Verbal to Nominal Domain

arXiv: https://arxiv.org/abs/2005.00278 · HTML: https://mlsanity.com/paper/2005.00278/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 May 2020.

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

- [QASem Parsing: Text-to-text Modeling of QA-based Semantics](https://mlsanity.com/paper/2205.11413/) (2022)
- [Unsupervised Mapping of Arguments of Deverbal Nouns to Their Corresponding Verbal Labels](https://mlsanity.com/paper/2306.13922/) (2023)
- [Exploring Non-Verbal Predicates in Semantic Role Labeling: Challenges and Opportunities](https://mlsanity.com/paper/2307.01870/) (2023)

## Abstract (arXiv)

Semantic role labeling (SRL) is an NLP task involving the assignment of predicate arguments to types, called semantic roles. Though research on SRL has primarily focused on verbal predicates and many resources available for SRL provide annotations only for verbs, semantic relations are often triggered by other linguistic constructions, e.g., nominalizations. In this work, we investigate a transfer scenario where we assume role-annotated data for the source verbal domain but only unlabeled data for the target nominal domain. Our key assumption, enabling the transfer between the two domains, is that selectional preferences of a role (i.e., preferences or constraints on the admissible arguments) do not strongly depend on whether the relation is triggered by a verb or a noun. For example, the same set of arguments can fill the Acquirer role for the verbal predicate `acquire' and its nominal form `acquisition'. We approach the transfer task from the variational autoencoding perspective. The labeler serves as an encoder (predicting role labels given a sentence), whereas selectional preferences are captured in the decoder component (generating arguments for the predicting roles). Nominal roles are not labeled in the training data, and the learning objective instead pushes the labeler to assign roles predictive of the arguments. Sharing the decoder parameters across the domains encourages consistency between labels predicted for both domains and facilitates the transfer. The method substantially outperforms baselines, such as unsupervised and `direct transfer' methods, on the English CoNLL-2009 dataset.