Large Language Models (LLMs) have recently demonstrated remarkable capabilities in
natural language processing tasks and beyond. This success of LLMs has led to a large …

With the advent of Web 2.0, there exist many online platforms that result in massive textual-
data production. With ever-increasing textual data at hand, it is of immense importance to …

So far, named entity recognition (NER) has been involved with three major types, including
flat, overlapped (aka. nested), and discontinuous NER, which have mostly been studied …

Pre-trained models have achieved state-of-the-art results in various Natural Language
Processing (NLP) tasks. Recent works such as T5 and GPT-3 have shown that scaling up …

Recently, the character-word lattice structure has been proved to be effective for Chinese
named entity recognition (NER) by incorporating the word information. However, since the …

We investigate a lattice-structured LSTM model for Chinese NER, which encodes a
sequence of input characters as well as all potential words that match a lexicon. Compared …

Named entity recognition (NER) is a well-studied task in natural language processing.
Traditional NER research only deals with flat entities and ignores nested entities. The span …

Recent pretraining models in Chinese neglect two important aspects specific to the Chinese
language: glyph and pinyin, which carry significant syntax and semantic information for …

The Bidirectional long short-term memory networks (BiLSTM) have been widely used as an
encoder in models solving the named entity recognition (NER) task. Recently, the …

We introduce a general framework for several information extraction tasks that share span
representations using dynamically constructed span graphs. The graphs are constructed by …