mlsanityData to 7 Oct 2026

Syntactic Nuclei in Dependency Parsing -- A Multilingual Exploration

arXiv 2101.11959 ↗First posted 28 Jan 2021cs.CLcited by 2

Not on the map. Why?

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.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 8 of its 38 references that are in the map. First posted on arXiv 28 Jan 2021.

Builds on

8 of 38 references.

References · 8

  1. 2020Universal Dependencies v2: An Evergrowing Multilingual Treebank Collectioncited by 269
  2. 2016Simple and Accurate Dependency Parsing Using Bidirectional LSTM Feature Representationscited by 55
  3. 2015Transition-Based Dependency Parsing with Stack Long Short-Term Memorycited by 45
  4. 201882 Treebanks, 34 Models: Universal Dependency Parsing with Multi-Treebank Modelscited by 11
  5. 2017Fast(er) Exact Decoding and Global Training for Transition-Based Dependency Parsing via a Minimal Feature Setcited by 5
  6. 2019Recursive Subtree Composition in LSTM-Based Dependency Parsingcited by 4
  7. 2019The (Non-)Utility of Structural Features in BiLSTM-based Dependency Parserscited by 3
  8. 2019What Should/Do/Can LSTMs Learn When Parsing Auxiliary Verb Constructions?cited by 1

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 1.

2 papers.