A Survey on Contextualised Semantic Shift Detection
arXiv:2304.01666 · doi:10.1145/3672393
Abstract
Semantic Shift Detection (SSD) is the task of identifying, interpreting, and assessing the possible change over time in the meanings of a target word. Traditionally, SSD has been addressed by linguists and social scientists through manual and time-consuming activities. In the recent years, computational approaches based on Natural Language Processing and word embeddings gained increasing attention to automate SSD as much as possible. In particular, over the past three years, significant advancements have been made almost exclusively based on word contextualised embedding models, which can handle the multiple usages/meanings of the words and better capture the related semantic shifts. In this paper, we survey the approaches based on contextualised embeddings for SSD (i.e., CSSDetection) and we propose a classification framework characterised by meaning representation, time-awareness, and learning modality dimensions. The framework is exploited i) to review the measures for shift assessment, ii) to compare the approaches on performance, and iii) to discuss the current issues in terms of scalability, interpretability, and robustness. Open challenges and future research directions about CSSDetection are finally outlined.
Acceted at ACM Computing Surveys
References in corpus (22)
- Efficient Estimation of Word Representations in Vector Space
- UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction
- Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
- Llama 2: Open Foundation and Fine-Tuned Chat Models
- Well-Read Students Learn Better: On the Importance of Pre-training Compact Models
- Adaptation of Deep Bidirectional Multilingual Transformers for Russian Language
- Analysing Lexical Semantic Change with Contextualised Word Representations
- Time-Out: Temporal Referencing for Robust Modeling of Lexical Semantic Change
- A State-of-the-Art of Semantic Change Computation
- Capturing Evolution in Word Usage: Just Add More Clusters?
- Latin BERT: A Contextual Language Model for Classical Philology
- Contextualized language models for semantic change detection: lessons learned
- Statistically significant detection of semantic shifts using contextual word embeddings
- HistBERT: A Pre-trained Language Model for Diachronic Lexical Semantic Analysis
- Frequency-based Distortions in Contextualized Word Embeddings
- Substitution-based Semantic Change Detection using Contextual Embeddings
- BOS at LSCDiscovery: Lexical Substitution for Interpretable Lexical Semantic Change Detection
- How BERT Speaks Shakespearean English? Evaluating Historical Bias in Contextual Language Models
- Incremental Affinity Propagation based on Cluster Consolidation and Stratification
- Survey in Characterizing Semantic Change
- A Semantic Distance Metric Learning approach for Lexical Semantic Change Detection
- Tracking Semantic Change in Slovene: A Novel Dataset and Optimal Transport-Based Distance