Current approaches for detecting text reuse do not focus on recontextualization, i.e., how the new context(s) of a reused text differs from its original context(s). In this paper, we propose a novel framework called TRoTR that relies on the notion of topic relatedness for evaluating the diachronic change of context in which text is reused. TRoTR includes two NLP tasks: TRiC and TRaC. TRiC is designed to evaluate the topic relatedness between a pair of recontextualizations. TRaC is designed to evaluate the overall topic variation within a set of recontextualizations. We also provide a curated TRoTR benchmark of biblical text reuse, human-annotated with topic relatedness. The benchmark exhibits an inter-annotator agreement of .811. We evaluate multiple, established SBERT models on the TRoTR tasks and find that they exhibit greater sensitivity to textual similarity than topic relatedness. Our experiments show that fine-tuning these models can mitigate such a kind of sensitivity.

Large Language Models (LLMs) offer an appealing alternative to training dedicated models for many Natural Language Processing (NLP) tasks. However, outdated knowledge and hallucination issues can be major obstacles in their application in knowledge-intensive biomedical scenarios. In this study, we consider the task of biomedical concept recognition (CR) from unstructured scientific literature and explore the use of Retrieval Augmented Generation (RAG) to improve accuracy and reliability of the LLM-based biomedical CR. Our approach, named REAL (Retrieval Augmented Entity Linking), combines the generative capabilities of LLMs with curated knowledge bases to automatically annotate natural language texts with concepts from bio-ontologies. By applying REAL to benchmark corpora on phenotype concept recognition, we show its effectiveness in improving LLM-based CR performance. This research highlights the potential of combining LLMs with external knowledge sources to advance biomedical text processing.

Contextual word embedding techniques for semantic shift detection are receiving more and more attention. In this paper, we present What is Done is Done (WiDiD), an incremental approach to semantic shift detection based on incremental clustering techniques and contextual embedding methods to capture the changes over the meanings of a target word along a diachronic corpus. In WiDiD, the word contexts observed in the past are consolidated as a set of clusters that constitute the “memory” of the word meanings observed so far. Such a memory is exploited as a basis for subsequent word observations, so that the meanings observed in the present are stratified over the past ones.

In this paper we present a new unsupervised approach, “Attraction to Topics” – A2T , for the detection of argumentative units, a sub-task of argument mining. Motivated by the importance of topic identification in manual annotation, we examine whether topic modeling can be used for performing unsupervised detection of argumentative sentences, and to what extend topic modeling can be used to classify sentences as claims and premises. Preliminary evaluation results suggest that topic information can be successfully used for the detection of argumentative sentences, at least for corpora used for evaluation. Our approach has been evaluated on two English corpora, the first of which contains 90 persuasive essays, while the second is a collection of 340 documents from user generated content.