Keyphrase Extraction from Scholarly Articles as Sequence Labeling using Contextualized Embeddings
This work addresses keyphrase extraction for scholarly articles, providing incremental improvements in performance through the use of contextualized embeddings.
The paper tackled keyphrase extraction from scholarly articles by formulating it as a sequence labeling task using a BiLSTM-CRF with contextualized embeddings, showing that contextualized embeddings like BERT and SciBERT outperform fixed embeddings and direct fine-tuning on benchmark datasets.
In this paper, we formulate keyphrase extraction from scholarly articles as a sequence labeling task solved using a BiLSTM-CRF, where the words in the input text are represented using deep contextualized embeddings. We evaluate the proposed architecture using both contextualized and fixed word embedding models on three different benchmark datasets (Inspec, SemEval 2010, SemEval 2017) and compare with existing popular unsupervised and supervised techniques. Our results quantify the benefits of (a) using contextualized embeddings (e.g. BERT) over fixed word embeddings (e.g. Glove); (b) using a BiLSTM-CRF architecture with contextualized word embeddings over fine-tuning the contextualized word embedding model directly, and (c) using genre-specific contextualized embeddings (SciBERT). Through error analysis, we also provide some insights into why particular models work better than others. Lastly, we present a case study where we analyze different self-attention layers of the two best models (BERT and SciBERT) to better understand the predictions made by each for the task of keyphrase extraction.