Keyword Extraction from Short Texts with a Text-To-Text Transfer Transformer
This work addresses keyword extraction for Polish short texts, particularly in scientific domains, but is incremental as it adapts an existing T5 model to a new language and dataset.
The paper tackled keyword extraction from short texts by applying a Polish T5 model (plT5kw) to a new corpus of 216,214 scientific abstracts, finding it yields promising results for both frequent and sparse keywords and performs well in cross-domain scenarios like news and dialog transcripts.
The paper explores the relevance of the Text-To-Text Transfer Transformer language model (T5) for Polish (plT5) to the task of intrinsic and extrinsic keyword extraction from short text passages. The evaluation is carried out on the new Polish Open Science Metadata Corpus (POSMAC), which is released with this paper: a collection of 216,214 abstracts of scientific publications compiled in the CURLICAT project. We compare the results obtained by four different methods, i.e. plT5kw, extremeText, TermoPL, KeyBERT and conclude that the plT5kw model yields particularly promising results for both frequent and sparsely represented keywords. Furthermore, a plT5kw keyword generation model trained on the POSMAC also seems to produce highly useful results in cross-domain text labelling scenarios. We discuss the performance of the model on news stories and phone-based dialog transcripts which represent text genres and domains extrinsic to the dataset of scientific abstracts. Finally, we also attempt to characterize the challenges of evaluating a text-to-text model on both intrinsic and extrinsic keyword extraction.