mlsanityData to 14 Oct 2026

Cross-domain Chinese Sentence Pattern Parsing

arXiv 2402.16311 ↗First posted 26 Feb 2024cs.CL cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Sentence Pattern Structure (SPS) parsing is a syntactic analysis method primarily employed in language teaching.Existing SPS parsers rely heavily on textbook corpora for training, lacking cross-domain capability.To overcome this constraint, this paper proposes an innovative approach leveraging large language models (LLMs) within a self-training framework. Partial syntactic rules from a source domain are combined with target domain sentences to dynamically generate training data, enhancing the adaptability of the parser to diverse domains.Experiments conducted on textbook and news domains demonstrate the effectiveness of the proposed method, outperforming rule-based baselines by 1.68 points on F1 metrics.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 25 of its 50 references that are in the map. First posted on arXiv 26 Feb 2024.

Builds on

25 of 50 references.

References · 25

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2020Measuring Massive Multitask Language Understandingcited by 7,963
  3. 2023Is ChatGPT a General-Purpose Natural Language Processing Task Solver?cited by 488
  4. 2016Deep Biaffine Attention for Neural Dependency Parsingcited by 334
  5. 2022News Summarization and Evaluation in the Era of GPT-3cited by 327
  6. 2018Constituency Parsing with a Self-Attentive Encodercited by 199
  7. 2019Revisiting Self-Training for Neural Sequence Generationcited by 155
  8. 2018Graph Convolution over Pruned Dependency Trees Improves Relation Extractioncited by 146
  9. 2020Neural Unsupervised Domain Adaptation in NLP---A Surveycited by 144
  10. 2023Automated Annotation with Generative AI Requires Validationcited by 76
  11. 2017A Minimal Span-Based Neural Constituency Parsercited by 59
  12. 2015Transition-Based Dependency Parsing with Stack Long Short-Term Memorycited by 45
13 more
  1. 2023Large Language Model Augmented Narrative Driven Recommendationscited by 31
  2. 2019Deep Contextualized Self-training for Low Resource Dependency Parsingcited by 24
  3. 2018What's Going On in Neural Constituency Parsers? An Analysiscited by 22
  4. 2019Cross-Domain Generalization of Neural Constituency Parserscited by 17
  5. 2022UniSumm and SummZoo: Unified Model and Diverse Benchmark for Few-Shot Summarizationcited by 15
  6. 2023Targeted Data Generation: Finding and Fixing Model Weaknessescited by 15
  7. 2022Task Compass: Scaling Multi-task Pre-training with Task Prefixcited by 14
  8. 2023Generation-driven Contrastive Self-training for Zero-shot Text Classification with Instruction-following LLMcited by 12
  9. 2016Shift-Reduce Constituent Parsing with Neural Lookahead Featurescited by 8
  10. 2023Explicit Syntactic Guidance for Neural Text Generationcited by 8
  11. 2019A Graph-based Model for Joint Chinese Word Segmentation and Dependency Parsingcited by 6
  12. 2020Feature Adaptation of Pre-Trained Language Models across Languages and Domains with Robust Self-Trainingcited by 4
  13. 2023LLM-enhanced Self-training for Cross-domain Constituency Parsingcited by 4

Built on by

Not cited yet.