Exploiting Diversity in Natural Language Processing: Combining Parsers
John C. Henderson, Eric Brill
Abstract
Three state-of-the-art statistical parsers are combined to produce more accurate parses, as well as new bounds on achievable Treebank parsing accuracy. Two general approaches are presented and two combination techniques are described for each approach. Both parametric and non-parametric models are explored. The resulting parsers surpass the best previously published performance results for the Penn Treebank.
Create a lesson
Related papers
Latent Compaction with Test-Time Training
Yingfa Chen, Xingyu Shen, Chaojun Xiao et al.
Manacá-1B-Instruct-2: Reproducible Safety Alignment for a Native Brazilian-Portuguese LLM. Negative DPO Results, a Controlled Composition Scan, and a Silent Failure Mode of the LLM Judge
Bruno Leonardo Santos Menezes, Carlos Leonardo Souza Cardoso, Fabio André Machado Porto
PerSo: Investigating Facets of LLMs' Social Intelligence in Real-World Persuasion Scenarios
Ali Zamani, Soroush Esfahanian, Erfan Shahabi et al.
PrismaCoder: Pushing the Boundaries of Open Multimodal Code Intelligence through Decomposed Rubric Synthesis
Qiushi Sun, Jingyang Gong, Yang Liu et al.
VASPO: Self-Distillation with Privileged Value Estimation
Fei Wu, Zhenrong Zhang, Jianshu Zhang et al.
ReaDy: Recurrent States as Dynamic Context for Speculative Drafting in Hybrid Linear Attention Large Language Models
Bohan Sun, Zunhai Su, Xialie Zhuang et al.