Keyword extraction is one of the core tasks in natural language processing. Classic extraction models are notorious for having a short attention span which make it hard for them to conclude relational connections among the words and sentences that are far from each other. This, in turn, makes their usage prohibitive for generating keywords that are inferred from the context of the whole text. In this paper, we explore using Large Language Models (LLMs) in generating keywords for items that are inferred from the items textual metadata. Our modeling framework includes several stages to fine grain the results by avoiding outputting keywords that are non informative or sensitive and reduce hallucinations common in LLM. We call our LLM-based framework Theme-Aware Keyword Extraction (LLM TAKE). We propose two variations of framework for generating extractive and abstractive themes for products in an E commerce setting. We perform an extensive set of experiments on three real data sets and show that our modeling framework can enhance accuracy based and diversity based metrics when compared with benchmark models.

For our course project, we aim to reverse the roles of the computer and human, such that the computer will act as an answerer and a human as a questioner. In the past, no such study has been conducted as this problem presented sophisticated challenges of Natural Language Inference and Textual Entailment. However, with the advent of transformer-based machine learning techniques such as BERT [1], RoBERTa [2], GPT-2 [3], and datasets such as BoolQ [4], such a model can be constructed. As this problem has not been formally defined, our goal is to formalize it and present preliminary results regarding the same. Furthermore, while there are several pre-trained question-answering models that select the start and end points of a corpus containing an answer, a simple yes/no answering task is surprisingly challenging and complex. A model for such a task would have to examine entailment as well as investigate if the corpus makes a positive answer to the question unlikely, even if it doesn't directly state a negative answer [4]. Our reverse Akinator model could be used for any sort of factual checker to examine whether a statement is true or not, given a knowledge corpus.