Dependency Parsing with Dynamic Bayesian Network
Virginia Savova, Leonid Peshkin
Abstract
Exact parsing with finite state automata is deemed inappropriate because of the unbounded non-locality languages overwhelmingly exhibit. We propose a way to structure the parsing task in order to make it amenable to local classification methods. This allows us to build a Dynamic Bayesian Network which uncovers the syntactic dependency structure of English sentences. Experiments with the Wall Street Journal demonstrate that the model successfully learns from labeled data.
Create a lesson
Related papers
Sparse Autoencoders for Mechanistic Interpretability in NLP: A Critical Survey of Recoverability, Interpretability, and Utility
Salima Lamsiyah, Adelaide Danilov, Oleksandr Marchenko Breneur et al.
Why Generate a Click? Plug-in Decision Heads for Web Agents
Chengguang Gan, Yunhao Liang, Hanjun Wei et al.
Language Exposure Matters: Distribution and Order in Multilingual BabyLM Pre-training
JiWoo Hwang, Lukas Edman, Alexander Fraser
AFCS: Atomic-Fact-Conditioned Synthesis for Factual Knowledge Pretraining
Yunhao Wang, Feng Zhang, Tinghao Yu et al.
Which Knowledge Should LLMs Trust? Uncovering a Generalizable Steering Direction Across Knowledge Conflicts
Yibin Lou, Yi Hu, Jianhui Chen et al.
What Is a Clarification? Estimating Model-Dependent Input Ambiguity
Jingqin Tang, Tim Tomov, Sebastian Schmidt et al.