BibTeX

@inProceedings{periti-tahmasebi-2024-systematic-337365,
	title        = {A Systematic Comparison of Contextualized Word Embeddings for Lexical Semantic Change},
	abstract     = {Contextualized embeddings are the preferred tool for modeling Lexical Semantic Change (LSC). Current evaluations typically focus on a specific task known as Graded Change Detection (GCD). However, performance comparison across work are often misleading due to their reliance on diverse settings. In this paper, we evaluate state-of-the-art models and approaches for GCD under equal conditions. We further break the LSC problem into Word-in-Context (WiC) and Word Sense Induction (WSI) tasks, and compare models across these different levels. Our evaluation is performed across different languages on eight available benchmarks for LSC, and shows that (i) APD outperforms other approaches for GCD; (ii) XL-LEXEME outperforms other contextualized models for WiC, WSI, and GCD, while being comparable to GPT-4; (iii) there is a clear need for improving the modeling of word meanings, as well as focus on how, when, and why these meanings change, rather than solely focusing on the extent of semantic change.},
	booktitle    = {Accepted for Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies},
	author       = {Periti, Francesco and Tahmasebi, Nina},
	year         = {2024},
	publisher    = {Association for Computational Linguistics},
}

@inProceedings{cassotti-etal-2024-computational-337360,
	title        = {Computational modeling of semantic change

},
	abstract     = {Languages change constantly over time, influenced by social, technological, cultural and political factors that affect how people express themselves. In particular, words can undergo the process of semantic change, which can be subtle and significantly impact the interpretation of texts. For example, the word terrific used to mean ‘causing terror’ and was as such synonymous to terrifying. Nowadays, speakers use the word in the sense of ‘excessive’ and even ‘amazing’. In Historical Linguistics, tools and methods have been developed to analyse this phenomenon, including systematic categorisations of the types of change, the causes and the mechanisms underlying the different types of change. However, traditional linguistic methods, while informative, are often based on small, carefully curated samples. Thanks to the availability of both large diachronic corpora, the computational means to model word meaning unsupervised, and evaluation benchmarks, we are seeing an increasing interest in the computational modelling of semantic change. This is evidenced by the increasing number of publications in this new domain as well as the organisation of initiatives and events related to this topic, such as four editions of the International Workshop on Computational Approaches to Historical Language Change LChange1, and several evaluation campaigns (Schlechtweg et al., 2020a; Basile et al., 2020b; Kutuzov et al.; Zamora-Reina et al., 2022).},
	booktitle    = {Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics: Tutorial Abstracts},
	author       = {Cassotti, Pierluigi and Periti, Francesco and De Pascale, Stefano and Dubossarsky, Haim and Tahmasebi, Nina},
	year         = {2024},
	publisher    = {Association for Computational Linguistics},
}

@inProceedings{periti-etal-2024-(chat)gpt-337358,
	title        = {(Chat)GPT v BERT Dawn of Justice for Semantic Change Detection},
	abstract     = {In the universe of Natural Language Processing, Transformer-based language models like BERT and (Chat)GPT have emerged as lexical superheroes with great power to solve open research problems. In this paper, we specifically focus on the temporal problem of semantic change, and evaluate their ability to solve two diachronic extensions of the Word-in-Context (WiC) task: TempoWiC and HistoWiC. In particular, we investigate the potential of a novel, off-the-shelf technology like ChatGPT (and GPT) 3.5 compared to BERT, which represents a family of models that currently stand as the state-of-the-art for modeling semantic change. Our experiments represent the first attempt to assess the use of (Chat)GPT for studying semantic change. Our results indicate that ChatGPT performs significantly worse than the foundational GPT version. Furthermore, our results demonstrate that (Chat)GPT achieves slightly lower performance than BERT in detecting long-term changes but performs significantly worse in detecting short-term changes.},
	booktitle    = {Findings of the Association for Computational Linguistics: EACL 2024},
	author       = {Periti, Francesco and Dubossarsky, Haim and Tahmasebi, Nina},
	year         = {2024},
	publisher    = {Association for Computational Linguistics},
}

@article{nielbo-etal-2024-quantitative-337356,
	title        = {Quantitative text analysis},
	abstract     = {Text analysis has undergone substantial evolution since its inception, moving from manual qualitative assessments to sophisticated quantitative and computational methods. Beginning in the late twentieth century, a surge in the utilization of computational techniques reshaped the landscape of text analysis, catalysed by advances in computational power and database technologies. Researchers in various fields, from history to medicine, are now using quantitative methodologies, particularly machine learning, to extract insights from massive textual data sets. This transformation can be described in three discernible methodological stages: feature-based models, representation learning models and generative models. Although sequential, these stages are complementary, each addressing analytical challenges in the text analysis. The progression from feature-based models that require manual feature engineering to contemporary generative models, such as GPT-4 and Llama2, signifies a change in the workflow, scale and computational infrastructure of the quantitative text analysis. This Primer presents a detailed introduction of some of these developments, offering insights into the methods, principles and applications pertinent to researchers embarking on the quantitative text analysis, especially within the field of machine learning.},
	journal      = {Nature Reviews Methods Primers},
	author       = {Nielbo, Kristoffer L. and Karsdorp, Folgert and Wevers, Melvin and Lassche, Alie and Baglini, Rebekah B. and Kestemont, Mike and Tahmasebi, Nina},
	year         = {2024},
	volume       = {4},
	number       = {1},
}

@inProceedings{schlechtweg-etal-2024-durel-336715,
	title        = {The DURel Annotation Tool: Human and Computational Measurement of Semantic Proximity, Sense Clusters and Semantic Change},
	abstract     = {We present the DURel tool implementing the annotation of semantic proximity between word uses into an online, open source interface. The tool supports standardized human annotation as well as computational annotation, building on recent advances with Word-in-Context models. Annotator judgments are clustered with automatic graph clustering techniques and visualized for analysis. This allows to measure word senses with simple and intuitive micro-task judgments between use pairs, requiring minimal preparation efforts. The tool offers additional functionalities to compare the agreement between annotators to guarantee the inter-subjectivity of the obtained judgments and to calculate summary statistics over the annotated data giving insights into sense frequency distributions, semantic variation or changes of senses over time.},
	booktitle    = {Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations.  St. Julians, Malta. Association for Computational Linguistics, pages 137–149},
	author       = {Schlechtweg, Dominik and Virk, Shafqat and Sander, Pauline and Sköldberg, Emma and Theuer Linke, Lukas and  Zhang, Tuo and Tahmasebi, Nina and  Schulte im Walde, Sabine},
	year         = {2024},
}