Enhancing Automatic Keyphrase Labelling with Text-to-Text Transfer Transformer (T5) Architecture: A Framework for Keyphrase Generation and Filtering

TL;DR

This paper introduces a T5-based framework for automatic keyphrase generation and filtering, significantly improving accuracy over existing methods by generating relevant keyphrases and effectively filtering irrelevant ones.

Contribution

The paper presents a novel T5-based keyphrase generation model and a filtering technique, enhancing the quality and relevance of generated keyphrases beyond prior extractive and generative approaches.

Findings

Model outperforms baselines with over 100% gains in some cases.

Filtering technique achieves near-perfect accuracy in removing false positives.

Majority voting improves keyphrase relevance and diversity.

Abstract

Automatic keyphrase labelling stands for the ability of models to retrieve words or short phrases that adequately describe documents' content. Previous work has put much effort into exploring extractive techniques to address this task; however, these methods cannot produce keyphrases not found in the text. Given this limitation, keyphrase generation approaches have arisen lately. This paper presents a keyphrase generation model based on the Text-to-Text Transfer Transformer (T5) architecture. Having a document's title and abstract as input, we learn a T5 model to generate keyphrases which adequately define its content. We name this model docT5keywords. We not only perform the classic inference approach, where the output sequence is directly selected as the predicted values, but we also report results from a majority voting approach. In this approach, multiple sequences are generated, and the keyphrases are ranked based on their frequency of occurrence across these sequences. Along with this model, we present a novel keyphrase filtering technique based on the T5 architecture. We train a T5 model to learn whether a given keyphrase is relevant to a document. We devise two evaluation methodologies to prove our model's capability to filter inadequate keyphrases. First, we perform a binary evaluation where our model has to predict if a keyphrase is relevant for a given document. Second, we filter the predicted keyphrases by several AKG models and check if the evaluation scores are improved. Experimental results demonstrate that our keyphrase generation model significantly outperforms all the baselines, with gains exceeding 100\% in some cases. The proposed filtering technique also achieves near-perfect accuracy in eliminating false positives across all datasets.