Scholarly knowledge graphs through structuring scholarly communication: a review

S Verma, R Bhatia, S Harit, S Batish - Complex & intelligent systems, 2023 - Springer
The necessity for scholarly knowledge mining and management has grown significantly as
academic literature and its linkages to authors produce enormously. Information extraction …

Revealing the technology development of natural language processing: A Scientific entity-centric perspective

H Zhang, C Zhang, Y Wang - Information Processing & Management, 2024 - Elsevier
Most studies on technology development have been conducted from a thematic perspective,
but the topics are coarse-grained and insufficient to accurately represent technology. The …

Transformers go for the LOLs: Generating (humourous) titles from scientific abstracts end-to-end

Y Chen, S Eger - arXiv preprint arXiv:2212.10522, 2022 - arxiv.org
We consider the end-to-end abstract-to-title generation problem, exploring seven recent
transformer based models (including ChatGPT) fine-tuned on more than 30k abstract-title …

[PDF][PDF] End-to-end construction of NLP knowledge graph

I Mondal, Y Hou, C Jochim - Findings of the Association for …, 2021 - aclanthology.org
This paper studies the end-to-end construction of an NLP Knowledge Graph (KG) from
scientific papers. We focus on extracting four types of relations: evaluatedOn between tasks …

Automated mining of leaderboards for empirical ai research

S Kabongo, J D'Souza, S Auer - … on Asia-Pacific Digital Libraries, ICADL …, 2021 - Springer
With the rapid growth of research publications, empowering scientists to keep an oversight
over scientific progress is of paramount importance. In this regard, the leaderboards facet of …

Zero-shot entailment of leaderboards for empirical ai research

S Kabongo, J D'Souza, S Auer - 2023 ACM/IEEE Joint …, 2023 - ieeexplore.ieee.org
We present a large-scale empirical investigation of the zero-shot learning phenomena in a
specific recognizing textual entailment (RTE) task category, ie, the automated mining of …

[PDF][PDF] Discovering data sets through machine learning: An ensemble approach to uncovering the prevalence of government-funded data sets

R Hausen, H Azarbonyad - Harvard Data Science Review, 2024 - assets.pubpub.org
The prevalence of government-funded dataset usage has yet to be comprehensively tracked
and understood. The lack of a standardized citation methodology has thus far prevented the …

Personal research knowledge graphs

P Chakraborty, S Dutta, DK Sanyal - Companion Proceedings of the …, 2022 - dl.acm.org
Maintaining research-related information in an organized manner can be challenging for a
researcher. In this paper, we envision personal research knowledge graphs (PRKGs) as a …

Aclm: A selective-denoising based generative data augmentation approach for low-resource complex ner

S Ghosh, U Tyagi, M Suri, S Kumar… - arXiv preprint arXiv …, 2023 - arxiv.org
Complex Named Entity Recognition (NER) is the task of detecting linguistically complex
named entities in low-context text. In this paper, we present ACLM Attention-map aware …

Named entity recognition as structured span prediction

U Zaratiana, N Tomeh, P Holat… - Proceedings of the …, 2022 - aclanthology.org
Abstract Named Entity Recognition (NER) is an important task in Natural Language
Processing with applications in many domains. While the dominant paradigm of NER is …