Large, pre-trained language models (PLMs) such as BERT and GPT have drastically
changed the Natural Language Processing (NLP) field. For numerous NLP tasks …

Entity and Relation Extraction (ERE) is an important task in information extraction. Recent
marker-based pipeline models achieve state-of-the-art performance, but still suffer from the …

Higher-order methods for dependency parsing can partially but not fully address the issue
that edges in dependency trees should be constructed at the text span/subtree level rather …

Dependency parsing aims to extract syntactic dependency structure or semantic
dependency structure for sentences. Existing methods for dependency parsing include …

Recent advances in multilingual language modeling have brought the idea of a truly
universal parser closer to reality. However, such models are still not immune to the “curse of …

Dependency parsing is an important fundamental natural language processing task which
analyzes the syntactic structure of an input sentence by illustrating the syntactic relations …

Dependency parsing is a crucial step towards deep language understanding and, therefore,
widely demanded by numerous Natural Language Processing applications. In particular, left …

The growing interaction between humans and machines raises the necessity to more
sophisticated tools for natural language understanding. Dependency parsing is crucial for …

Prior works on joint Information Extraction (IE) typically model instance (eg, event triggers,
entities, roles, relations) interactions by representation enhancement, type dependencies …

We propose a new method for projective dependency parsing based on headed spans. In a
projective dependency tree, the largest subtree rooted at each word covers a contiguous …