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

Relation extraction (RE) involves identifying the relations between entities from underlying
content. RE serves as the foundation for many natural language processing (NLP) and …

Prompt tuning, which only tunes continuous prompts with a frozen language model,
substantially reduces per-task storage and memory usage at training. However, in the …

Deep learning models can accurately predict molecular properties and help making the
search for potential drug candidates faster and more efficient. Many existing methods are …

Prevalent supervised learning methods in natural language processing (NLP) are
notoriously data-hungry, which demand large amounts of high-quality annotated data. In …

We introduce a method for improving the structural understanding abilities of language
models. Unlike previous approaches that finetune the models with task-specific …

The challenge of information extraction (IE) lies in the diversity of label schemas and the
heterogeneity of structures. Traditional methods require task-specific model design and rely …

Text classification is a fundamental problem in information retrieval with many real-world
applications, such as predicting the topics of online articles and the categories of e …

Relation extraction (RE) consistently involves a certain degree of labeled or unlabeled data
even if under zero-shot setting. Recent studies have shown that large language models …

Document-level Relation Triplet Extraction (DocRTE) is a fundamental task in information
systems that aims to simultaneously extract entities with semantic relations from a document …