Necva Bölücü, Maciej Rybinski, Stephen Wan. Findings of the Association for Computational Linguistics: EMNLP 2023. 2023.

Food extrusion is a widely used processing technique that transforms raw ingredients into structured food products—foods with well-defined textures, shapes, and functionalities—through mechanical shear and thermal energy. Despite its broad industrial application, the absence of a standardised, structured dataset capturing extrusion research parameters has hindered research synthesis, product development, and process optimisation. To address this gap, we introduce a manually curated food extrusion literature dataset capturing publication details, product types, process parameters, formulation data, experimental variables, characterisation metrics, and study-level insights. However, while manually curated datasets are typically of high quality, their scope is limited by time and resource constraints. We propose a method to supplement the dataset using large language models (LLMs) and evaluate the accuracy of LLMs in extracting structured food extrusion data from the scientific literature. Our findings demonstrate that LLMs can effectively extract structured information. However, some challenges, such as hallucination and missing contextual details, remain, suggesting that human effort can be spent on validating the resulting data. This still represents significant time savings as validation is a less time-consuming task than data extraction. We argue that LLMs thus represent a viable tool in providing supplementary datasets, and we propose a method to leverage existing human efforts in dataset creation to improve data quality.

Social media plays an important role in expressing the thoughts and sentiments of users. Irony is a way of stating a sentiment about something by expressing the opposite of the intended literal meaning. Irony detection is a recent emerging task in low-resource languages, although other tasks related to sentiment, such as sentiment analysis and emotion detection, have been widely tackled. In this study, we investigate Graph Neural Networks (GNNs) for irony detection in Turkish, a low-resource language in sentiment-related tasks. We incorporate semantic information into the GNNs using the Universal Conceptual Cognitive Annotation (UCCA) framework. Extensive experimental results and in-depth analysis show that our models outperform state-of-the-art irony detection models in Turkish. Our UCCA-GAT (UCCA-Graph Attention Network) model achieves an F ₁ -score of 94.85% (7.362% gain over the state-of-the-art) on the Turkish-Irony-Dataset and an accuracy of 72.82% (4.39% gain over the state-of-the-art) on the IronyTR Dataset. We also provide a comprehensive analysis of the proposed models to understand their limitations. ¹