# Cross-Domain Generalization of Neural Constituency Parsers

arXiv: https://arxiv.org/abs/1907.04347 · HTML: https://mlsanity.com/paper/1907.04347/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Jul 2019.

## Built on by (most cited first, 17 of 17)

- [BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions](https://mlsanity.com/paper/2406.15877/) (2024)
- [Mind the Gap: Assessing Temporal Generalization in Neural Language Models](https://mlsanity.com/paper/2102.01951/) (2021)
- [Grounding Language Models to Images for Multimodal Inputs and Outputs](https://mlsanity.com/paper/2301.13823/) (2023)
- [State-of-the-art generalisation research in NLP: A taxonomy and review](https://mlsanity.com/paper/2210.03050/) (2022)
- [Video-aided Unsupervised Grammar Induction](https://mlsanity.com/paper/2104.04369/) (2021)
- [Generalization Analogies: A Testbed for Generalizing AI Oversight to Hard-To-Measure Domains](https://mlsanity.com/paper/2311.07723/) (2023)
- [Beyond Borders: Investigating Cross-Jurisdiction Transfer in Legal Case Summarization](https://mlsanity.com/paper/2403.19317/) (2024)
- [Investigating Non-local Features for Neural Constituency Parsing](https://mlsanity.com/paper/2109.12814/) (2021)
- [LLM-enhanced Self-training for Cross-domain Constituency Parsing](https://mlsanity.com/paper/2311.02660/) (2023)
- [Benchmarking Akan ASR Models Across Domain-Specific Datasets: A Comparative Evaluation of Performance, Scalability, and Adaptability](https://mlsanity.com/paper/2507.02407/) (2025)
- [Generalizing to Unseen Domains with Wasserstein Distributional Robustness under Limited Source Knowledge](https://mlsanity.com/paper/2207.04913/) (2022)
- [Out-of-Distribution Generalization in Text Classification: Past, Present, and Future](https://mlsanity.com/paper/2305.14104/) (2023)
- [Multi-Source (Pre-)Training for Cross-Domain Measurement, Unit and Context Extraction](https://mlsanity.com/paper/2308.02951/) (2023)
- [Cross-domain Chinese Sentence Pattern Parsing](https://mlsanity.com/paper/2402.16311/) (2024)
- [Contrastive Learning on LLM Back Generation Treebank for Cross-domain Constituency Parsing](https://mlsanity.com/paper/2505.20976/) (2025)
- [Lexicalized Constituency Parsing for Middle Dutch: Low-resource Training and Cross-Domain Generalization](https://mlsanity.com/paper/2601.07008/) (2026)
- [Representing and Parsing Korean Constituency Structure at Different Levels of Granularity](https://mlsanity.com/paper/2608.27035/) (2026)

## Abstract (arXiv)

Neural parsers obtain state-of-the-art results on benchmark treebanks for constituency parsing -- but to what degree do they generalize to other domains? We present three results about the generalization of neural parsers in a zero-shot setting: training on trees from one corpus and evaluating on out-of-domain corpora. First, neural and non-neural parsers generalize comparably to new domains. Second, incorporating pre-trained encoder representations into neural parsers substantially improves their performance across all domains, but does not give a larger relative improvement for out-of-domain treebanks. Finally, despite the rich input representations they learn, neural parsers still benefit from structured output prediction of output trees, yielding higher exact match accuracy and stronger generalization both to larger text spans and to out-of-domain corpora. We analyze generalization on English and Chinese corpora, and in the process obtain state-of-the-art parsing results for the Brown, Genia, and English Web treebanks.