Pre-trained language models (PLMs) such as GPTs have been revealed to be biased
towards certain target classes because of the prompt and the model's intrinsic biases. In …

In this paper, we explore the question of whether large language models can support cost-
efficient information extraction from tables. We introduce schema-driven information …

Extracting structured information from all manner of webpages is an important problem with
the potential to automate many real-world applications. Recent work has shown the …

Ad hoc table retrieval refers to the task of performing semantic matching between given
queries and candidate tables. In recent years, the approach to addressing this retrieval task …

We present OpenTriage, a system for extracting structured entities from detail Web pages of
several sites and finding linkages between the extracted data. The system builds an …

Extracting data from Web sites is still a challenge since pages have a complex and
changeable structure, and the reason is simple: Web pages are designed to be visually user …

As with all the Ph. D. stories, my Ph. D. journey has its ups and downs, and will be a forever
cherished memory for the rest of my life. First and foremost, I would like to give special …

Structured information extraction from the Web plays an important role in many large-scale
automated systems, required to enable varying downstream applications. In this thesis, we …