Data scarcity has been the main factor that hinders the progress of event extraction. To
overcome this issue, we propose a Self-Training with Feedback (STF) framework that …

Previous methods based on Large Language Models (LLM) perform unsupervised
dependency parsing by maximizing bi-lexical dependence scores. However, these previous …

Hidden Markov Models (HMMs) and Probabilistic Context-Free Grammars (PCFGs) are
widely used structured models, both of which can be represented as factor graph grammars …

Scaling dense PCFGs to thousands of nonterminals via a low-rank parameterization of the
rule probability tensor has been shown to be beneficial for unsupervised parsing. However …

Human language is known to exhibit a nested, hierarchical structure, allowing us to form
complex sentences out of smaller pieces. However, many state-of-the-art neural networks …

Data scarcity has been the main factor that hinders the progress of event extraction. To
overcome this issue, we propose a Self-Training with Feedback (STF) framework that …

Human language is full of compositional syntactic structures, and although neural networks
have contributed to groundbreaking improvements in computer systems that process …

Injecting human knowledge into neural networks is a crucial but non-trivial task as neural
networks are often treated as a black-box function, making their inner workings …