Text sampling strategies for predicting missing bibliographic links

Abstract

The paper proposes various strategies for sampling text data when performing automatic sentence classification for the purpose of detecting missing bibliographic links. We construct samples based on sentences as semantic units of the text and add their immediate context which consists of several neighbouring sentences. We examine a number of sampling strategies that differ in context size and position. The experiment is carried out on the collection of STEM scientific papers. Including the context of sentences into samples improves the result of their classification. We automatically determine the optimal sampling strategy for a given text collection by implementing an ensemble voting when classifying the same data sampled in different ways. Sampling strategy taking into account the sentence context with hard voting procedure leads to the classification accuracy of 98% (F1-score). This method of detecting missing bibliographic links can be used in recommendation engines of applied intelligent information systems. Keywords: text sampling, sampling strategy, citation analysis, bibliographic link prediction, sentence classification.

Who Are All The Stochastic Parrots Imitating? They Should Tell Us!

“…Citation Generation Although LMs, particularly those intended to produce scientific text, such as Meta's Galactica (Taylor et al, 2022), already produce text that looks as if it is a citation, frequently there is no document corresponding to the apparent citation or the cited document does not support the statement associated with it. Many existing approaches to citation recommendation offer productive avenues to explore for factuality testing, post-hoc generation of support, hybrid architectures, or creation of training data (Ali et al, 2022;Krasnova et al, 2023). There has also been work on citation generation, where the task is either: 1) given two documents, generate an explanation for the relation between them (Luu et al, 2020), or 2) generate a citation for an already existing text (Gu and Hahnloser, 2022;Xing et al, 2020;Wu et al, 2021;Fetahu et al, 2016).…”