# Syntactic Nuclei in Dependency Parsing -- A Multilingual Exploration

arXiv: https://arxiv.org/abs/2101.11959 · HTML: https://mlsanity.com/paper/2101.11959/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 38 references that are in the map.
- First posted on arXiv 28 Jan 2021.

## Builds on (most cited first, 8 of 8)

- [Universal Dependencies v2: An Evergrowing Multilingual Treebank Collection](https://mlsanity.com/paper/2004.10643/) (2020)
- [Simple and Accurate Dependency Parsing Using Bidirectional LSTM Feature Representations](https://mlsanity.com/paper/1603.04351/) (2016)
- [Transition-Based Dependency Parsing with Stack Long Short-Term Memory](https://mlsanity.com/paper/1505.08075/) (2015)
- [82 Treebanks, 34 Models: Universal Dependency Parsing with Multi-Treebank Models](https://mlsanity.com/paper/1809.02237/) (2018)
- [Fast(er) Exact Decoding and Global Training for Transition-Based Dependency Parsing via a Minimal Feature Set](https://mlsanity.com/paper/1708.09403/) (2017)
- [Recursive Subtree Composition in LSTM-Based Dependency Parsing](https://mlsanity.com/paper/1902.09781/) (2019)
- [The (Non-)Utility of Structural Features in BiLSTM-based Dependency Parsers](https://mlsanity.com/paper/1905.12676/) (2019)
- [What Should/Do/Can LSTMs Learn When Parsing Auxiliary Verb Constructions?](https://mlsanity.com/paper/1907.07950/) (2019)

## Built on by (most cited first, 2 of 2)

- [Morphology Without Borders: Clause-Level Morphology](https://mlsanity.com/paper/2202.12832/) (2022)
- [Transition-based Bubble Parsing: Improvements on Coordination Structure Prediction](https://mlsanity.com/paper/2107.06905/) (2021)

## Abstract (arXiv)

Standard models for syntactic dependency parsing take words to be the elementary units that enter into dependency relations. In this paper, we investigate whether there are any benefits from enriching these models with the more abstract notion of nucleus proposed by Tesni`ere. We do this by showing how the concept of nucleus can be defined in the framework of Universal Dependencies and how we can use composition functions to make a transition-based dependency parser aware of this concept. Experiments on 12 languages show that nucleus composition gives small but significant improvements in parsing accuracy. Further analysis reveals that the improvement mainly concerns a small number of dependency relations, including nominal modifiers, relations of coordination, main predicates, and direct objects.