# Dependency Parsing as Head Selection

arXiv: https://arxiv.org/abs/1606.01280 · HTML: https://mlsanity.com/paper/1606.01280/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Jun 2016.

## Built on by (most cited first, 13 of 13)

- [Exploring Large Language Models for Classical Philology](https://mlsanity.com/paper/2305.13698/) (2023)
- [A Conditional Splitting Framework for Efficient Constituency Parsing](https://mlsanity.com/paper/2106.15760/) (2021)
- [Dependency Parsing with Bottom-up Hierarchical Pointer Networks](https://mlsanity.com/paper/2105.09611/) (2021)
- [JaMIE: A Pipeline Japanese Medical Information Extraction System](https://mlsanity.com/paper/2111.04261/) (2021)
- [Structural generalization in COGS: Supertagging is (almost) all you need](https://mlsanity.com/paper/2310.14124/) (2023)
- [Instance-Based Neural Dependency Parsing](https://mlsanity.com/paper/2109.13497/) (2021)
- [Generating CCG Categories](https://mlsanity.com/paper/2103.08139/) (2021)
- [On the inconsistency of separable losses for structured prediction](https://mlsanity.com/paper/2301.10810/) (2023)
- [On graph-based reentrancy-free semantic parsing](https://mlsanity.com/paper/2302.07679/) (2023)
- [Heidelberg-Boston @ SIGTYP 2024 Shared Task: Enhancing Low-Resource Language Analysis With Character-Aware Hierarchical Transformers](https://mlsanity.com/paper/2405.20145/) (2024)
- [Hierarchical Multitask Learning with Dependency Parsing for Japanese Semantic Role Labeling Improves Performance of Argument Identification](https://mlsanity.com/paper/2101.06071/) (2021)
- [Syntactic Inductive Biases for Deep Learning Methods](https://mlsanity.com/paper/2206.04806/) (2022)
- [A Joint Neural Baseline for Concept, Assertion, and Relation Extraction from Clinical Text](https://mlsanity.com/paper/2603.07487/) (2026)

## Abstract (arXiv)

Conventional graph-based dependency parsers guarantee a tree structure both during training and inference. Instead, we formalize dependency parsing as the problem of independently selecting the head of each word in a sentence. Our model which we call textscDeNSe (as shorthand for bf Dependency bf Neural bf Selection) produces a distribution over possible heads for each word using features obtained from a bidirectional recurrent neural network. Without enforcing structural constraints during training, textscDeNSe generates (at inference time) trees for the overwhelming majority of sentences, while non-tree outputs can be adjusted with a maximum spanning tree algorithm. We evaluate textscDeNSe on four languages (English, Chinese, Czech, and German) with varying degrees of non-projectivity. Despite the simplicity of the approach, our parsers are on par with the state of the art.