# Deep Contextualized Self-training for Low Resource Dependency Parsing

arXiv: https://arxiv.org/abs/1911.04286 · HTML: https://mlsanity.com/paper/1911.04286/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Nov 2019.

## Built on by (most cited first, 24 of 24)

- [A Comprehensive Survey on Source-free Domain Adaptation](https://mlsanity.com/paper/2302.11803/) (2023)
- [Deep Unsupervised Domain Adaptation: A Review of Recent Advances and Perspectives](https://mlsanity.com/paper/2208.07422/) (2022)
- [DoCoGen: Domain Counterfactual Generation for Low Resource Domain Adaptation](https://mlsanity.com/paper/2202.12350/) (2022)
- [UDALM: Unsupervised Domain Adaptation through Language Modeling](https://mlsanity.com/paper/2104.07078/) (2021)
- [Example-based Hypernetworks for Out-of-Distribution Generalization](https://mlsanity.com/paper/2203.14276/) (2022)
- [Multi-task Active Learning for Pre-trained Transformer-based Models](https://mlsanity.com/paper/2208.05379/) (2022)
- [Zero-shot Transfer of Article-aware Legal Outcome Classification for European Court of Human Rights Cases](https://mlsanity.com/paper/2302.00609/) (2023)
- [Measuring the Robustness of NLP Models to Domain Shifts](https://mlsanity.com/paper/2306.00168/) (2023)
- [A Little Pretraining Goes a Long Way: A Case Study on Dependency Parsing Task for Low-resource Morphologically Rich Languages](https://mlsanity.com/paper/2102.06551/) (2021)
- [Not All Linearizations Are Equally Data-Hungry in Sequence Labeling Parsing](https://mlsanity.com/paper/2108.07556/) (2021)
- [Model Compression for Domain Adaptation through Causal Effect Estimation](https://mlsanity.com/paper/2101.07086/) (2021)
- [Explainable Misinformation Detection Across Multiple Social Media Platforms](https://mlsanity.com/paper/2203.11724/) (2022)
- [Meta-Tsallis-Entropy Minimization: A New Self-Training Approach for Domain Adaptation on Text Classification](https://mlsanity.com/paper/2308.02746/) (2023)
- [LLM-enhanced Self-training for Cross-domain Constituency Parsing](https://mlsanity.com/paper/2311.02660/) (2023)
- [Systematic Investigation of Strategies Tailored for Low-Resource Settings for Low-Resource Dependency Parsing](https://mlsanity.com/paper/2201.11374/) (2022)
- [Learning Discrete Structured Variational Auto-Encoder using Natural Evolution Strategies](https://mlsanity.com/paper/2205.01324/) (2022)
- [Revealing the impact of synthetic native samples and multi-tasking strategies in Hindi-English code-mixed humour and sarcasm detection](https://mlsanity.com/paper/2412.12761/) (2024)
- [STAD: Self-Training with Ambiguous Data for Low-Resource Relation Extraction](https://mlsanity.com/paper/2209.01431/) (2022)
- [Examining the Effect of Pre-training on Time Series Classification](https://mlsanity.com/paper/2309.05256/) (2023)
- [Early stopping by correlating online indicators in neural networks](https://mlsanity.com/paper/2402.02513/) (2024)
- [Absolute convergence and error thresholds in non-active adaptive sampling](https://mlsanity.com/paper/2402.02522/) (2024)
- [Cross-domain Chinese Sentence Pattern Parsing](https://mlsanity.com/paper/2402.16311/) (2024)
- [CSSL: Contrastive Self-Supervised Learning for Dependency Parsing on Relatively Free Word Ordered and Morphologically Rich Low Resource Languages](https://mlsanity.com/paper/2410.06944/) (2024)
- [Lexicalized Constituency Parsing for Middle Dutch: Low-resource Training and Cross-Domain Generalization](https://mlsanity.com/paper/2601.07008/) (2026)

## Abstract (arXiv)

Neural dependency parsing has proven very effective, achieving state-of-the-art results on numerous domains and languages. Unfortunately, it requires large amounts of labeled data, that is costly and laborious to create. In this paper we propose a self-training algorithm that alleviates this annotation bottleneck by training a parser on its own output. Our Deep Contextualized Self-training (DCST) algorithm utilizes representation models trained on sequence labeling tasks that are derived from the parser's output when applied to unlabeled data, and integrates these models with the base parser through a gating mechanism. We conduct experiments across multiple languages, both in low resource in-domain and in cross-domain setups, and demonstrate that DCST substantially outperforms traditional self-training as well as recent semi-supervised training methods.