Florentina Hristea

Mihaela Petre-Vlad, Cornelia Caragea, Florentina Hristea. Findings of the Association for Computational Linguistics: EMNLP 2025. 2025.

Natural language processing (NLP) is one of the most important technologies in use today, especially due to the large and growing amount of online text, which needs to be understood in order to fully ascertain its enormous value

Hate Speech is a frequent problem occurring among Internet users. Recent regulations are being discussed by U.K. representatives (“Online Safety Bill”) and by the European Commission, which plans on introducing Hate Speech as an “EU crime”. The recent legislation having passed in order to combat this kind of speech places the burden of identification on the hosting websites and often within a tight time frame (24 h in France and Germany). These constraints make automatic Hate Speech detection a very important topic for major social media platforms. However, recent literature on Hate Speech detection lacks a benchmarking system that can evaluate how different approaches compare against each other regarding the prediction made concerning different types of text (short snippets such as those present on Twitter, as well as lengthier fragments). This paper intended to deal with this issue and to take a step forward towards the standardization of testing for this type of natural language processing (NLP) application. Furthermore, this paper explored different transformer and LSTM-based models in order to evaluate the performance of multi-task and transfer learning models used for Hate Speech detection. Some of the results obtained in this paper surpassed the existing ones. The paper concluded that transformer-based models have the best performance on all studied Datasets.

Summary: The issue of whether or not word sense disambiguation (WSD) can improve information retrieval (IR) results has been intensely debated over the years, with many inconclusive or contradictory results and a majority of skeptical opinions. All three classes of WSD methods (supervised, unsupervised, and knowledge‐based) have been considered by the literature with respect to IR. We hereby survey the unsupervised approach which, although relatively rarely used, has provided positive results at a large scale. Unsupervised WSD has already made proof of its utility in IR and it is our belief that it still holds a promise for this field. The two main existing types of unsupervised methods for IR, which are of completely different natures, are presented, within the scientific context in which they were born, and are compared. Regardless of the gap in time between these central approaches, we are of the opinion that the unsupervised solution to the discussed problem remains the most significant for IR applications. By surveying what we consider the most promising existing approach to usage of WSD in IR, and by discussing its possible extensions, we hope to stimulate continuation of this line of research, possibly at an even more successful level.

Whether or not word sense disambiguation (WSD) can improve information retrieval (IR) results represents a topic that has been intensely debated over the years, with many inconclusive or contradictory conclusions. The most rarely used type of WSD for this task is the unsupervised one, although it has been proven to be beneficial at a large scale. Our study builds on existing research and tries to improve the most recent unsupervised method which is based on spectral clustering. It investigates the possible benefits of “helping” spectral clustering through feature selection when it performs sense discrimination for IR. Results obtained so far, involving large data collections, encourage us to point out the importance of feature selection even in the case of this advanced, state of the art clustering technique that is known for performing its own feature weighting. By suggesting an improvement of what we consider the most promising approach to usage of WSD in IR, and by commenting on its possible extensions, we state that WSD still holds a promise for IR and hope to stimulate continuation of this line of research, perhaps at an even more successful level.

In this paper, we present a novel unsupervised algorithm for word sense disambiguation (WSD) at the document level. Our algorithm is inspired by a widely-used approach in the field of genetics for whole genome sequencing, known as the Shotgun sequencing technique. The proposed WSD algorithm is based on three main steps. First, a brute-force WSD algorithm is applied to short context windows (up to 10 words) selected from the document in order to generate a short list of likely sense configurations for each window. In the second step, these local sense configurations are assembled into longer composite configurations based on suffix and prefix matching. The resulted configurations are ranked by their length, and the sense of each word is chosen based on a voting scheme that considers only the top k configurations in which the word appears. We compare our algorithm with other state-of-the-art unsupervised WSD algorithms and demonstrate better performance, sometimes by a very large margin. We also show that our algorithm can yield better performance than the Most Common Sense (MCS) baseline on one data set. Moreover, our algorithm has a very small number of parameters, is robust to parameter tuning, and, unlike other bio-inspired methods, it gives a deterministic solution (it does not involve random choices).

The present paper concentrates on the issue of feature selection for unsupervised word sense disambiguation (WSD) performed with an underlying Naïve Bayes model. It introduces dependency-based feature selection which, to our knowledge, is used for th

The present paper extends a new word sense disambiguation method [9] to the case of adjectives. The method lies at the border between unsupervised and knowledge-based techniques. It performs unsupervised word sense disambiguation based on an underlying Naïve Bayes model, while using WordNet as knowledge source for feature selection. The proposed extension of the disambiguation method makes ample use of the WordNet semantic relations that are typical of adjectives. Its performance is compared to that of previous approaches that rely on completely different feature sets. Test results show that feature selection using a knowledge source of type WordNet is more effective in the disambiguation of adjective senses than local type features (like part-of-speech tags) are.