# Lexicalized Constituency Parsing for Middle Dutch: Low-resource Training and Cross-Domain Generalization

arXiv: https://arxiv.org/abs/2601.07008 · HTML: https://mlsanity.com/paper/2601.07008/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 77 references that are in the map.
- First posted on arXiv 11 Jan 2026.

## Builds on (most cited first, 24 of 24)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [Don't Stop Pretraining: Adapt Language Models to Domains and Tasks](https://mlsanity.com/paper/2004.10964/) (2020)
- [Domain Separation Networks](https://mlsanity.com/paper/1608.06019/) (2016)
- [Constituency Parsing with a Self-Attentive Encoder](https://mlsanity.com/paper/1805.01052/) (2018)
- [Neural Unsupervised Domain Adaptation in NLP---A Survey](https://mlsanity.com/paper/2006.00632/) (2020)
- [Multilingual Constituency Parsing with Self-Attention and Pre-Training](https://mlsanity.com/paper/1812.11760/) (2018)
- [Low-Resource Domain Adaptation for Compositional Task-Oriented Semantic Parsing](https://mlsanity.com/paper/2010.03546/) (2020)
- [Learning What and Where to Transfer](https://mlsanity.com/paper/1905.05901/) (2019)
- [Head-Driven Phrase Structure Grammar Parsing on Penn Treebank](https://mlsanity.com/paper/1907.02684/) (2019)
- [Extending a Parser to Distant Domains Using a Few Dozen Partially Annotated Examples](https://mlsanity.com/paper/1805.06556/) (2018)
- [Neural Segmental Hypergraphs for Overlapping Mention Recognition](https://mlsanity.com/paper/1810.01817/) (2018)
- [Deep Contextualized Self-training for Low Resource Dependency Parsing](https://mlsanity.com/paper/1911.04286/) (2019)
- [Nested Named Entity Recognition with Partially-Observed TreeCRFs](https://mlsanity.com/paper/2012.08478/) (2020)
- [What's Going On in Neural Constituency Parsers? An Analysis](https://mlsanity.com/paper/1804.07853/) (2018)
- [Bottom-Up Constituency Parsing and Nested Named Entity Recognition with Pointer Networks](https://mlsanity.com/paper/2110.05419/) (2021)
- [Span-Based Constituency Parsing with a Structure-Label System and Provably Optimal Dynamic Oracles](https://mlsanity.com/paper/1612.06475/) (2016)
- [Cross-Domain Generalization of Neural Constituency Parsers](https://mlsanity.com/paper/1907.04347/) (2019)
- [How to best use Syntax in Semantic Role Labelling](https://mlsanity.com/paper/1906.00266/) (2019)
- [Encoding Syntactic Constituency Paths for Frame-Semantic Parsing with Graph Convolutional Networks](https://mlsanity.com/paper/2011.13210/) (2020)
- [Robust Semantic Parsing with Adversarial Learning for Domain Generalization](https://mlsanity.com/paper/1910.06700/) (2019)
- [Penn-Helsinki Parsed Corpus of Early Modern English: First Parsing Results and Analysis](https://mlsanity.com/paper/2112.08532/) (2021)
- [Cross-Lingual Constituency Parsing for Middle High German: A Delexicalized Approach](https://mlsanity.com/paper/2308.04645/) (2023)

## Abstract (arXiv)

Recent years have seen growing interest in applying neural networks and contextualized word embeddings to the parsing of historical languages. However, most advances have focused on dependency parsing, while constituency parsing for low-resource historical languages like Middle Dutch has received little attention. In this paper, we adapt a transformer-based constituency parser to Middle Dutch, a highly heterogeneous and low-resource language, and investigate methods to improve both its in-domain and cross-domain performance. We show that joint training with higher-resource auxiliary languages increases F1 scores by up to 0.73, with the greatest gains achieved from languages that are geographically and temporally closer to Middle Dutch. We further evaluate strategies for leveraging newly annotated data from additional domains, finding that fine-tuning and data combination yield comparable improvements, and our neural parser consistently outperforms the currently used PCFG-based parser for Middle Dutch. We further explore feature-separation techniques for domain adaptation and demonstrate that a minimum threshold of approximately 200 examples per domain is needed to effectively enhance cross-domain performance.