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 …

Current generative knowledge graph construction approaches usually fail to capture
structural knowledge by simply flattening natural language into serialized texts or a …

Abstract Knowledge mining is a widely active research area across disciplines such as
natural language processing (NLP), data mining (DM), and machine learning (ML). The …

Symbolic knowledge graphs (KGs) have been constructed either by expensive human
crowdsourcing or with complex text mining pipelines. The emerging large pretrained …

Over the last decade, several regulatory bodies have started requiring the disclosure of non-
financial information from publicly listed companies, in light of the investors' increasing …

Using prompts to explore the knowledge contained within pre-trained language models for
downstream tasks has now become an active topic. Current prompt tuning methods mostly …

Open information extraction is an important NLP task that targets extracting structured
information from unstructured text without limitations on the relation type or the domain of the …

A major challenge in deep learning (DL) model training is data scarcity. Data scarcity is
commonly found in specific domains, such as clinical or low-resource languages, that are …

Pre-trained language models have demonstrated impressive performance in both natural
language processing and program understanding, which represent the input as a token …