Representation Learning for Resource-Constrained Keyphrase Generation

Abstract

State-of-the-art keyphrase generation methods generally depend on large annotated datasets, limiting their performance in domains with constrained resources. To overcome this challenge, we investigate strategies to learn an intermediate representation suitable for the keyphrase generation task. We introduce salient span recovery and salient span prediction as guided denoising language modeling objectives that condense the domainspecific knowledge essential for keyphrase generation. Through experiments on multiple scientific keyphrase generation benchmarks, we show the effectiveness of the proposed approach for facilitating low-resource and zeroshot keyphrase generation. Furthermore, we observe that our method especially benefits the generation of absent keyphrases, approaching the performance of SOTA methods trained with large training sets.

Unsupervised Term Extraction for Highly Technical Domains

“…What we describe in this work is an effective term extraction approach that is fully unsupervised and also offers the flexibility and modularity to deploy and easily maintain systems in production. ATE should not be confused with keyphrase extraction (Firoozeh et al, 2020;Mahata et al, 2018;Bennani-Smires et al, 2018) and keyphrase generation (Wu et al, 2022;Chen et al, 2020), which have the goal of extracting, or generating, key phrases that best describe a given free text document. Keyphrases can be seen as a set of tags associated to a document.…”