Abstract
In recent years, Lexical semantic change detection (LSCD) has become a central task of NLP. Because most studies in LSCD only consider the semantic change of words in isolation, in this paper, we propose a new direction for the analysis of semantic shifts: traveling word pairs. First, we introduce shift correlation to find pairs of words that semantically shift together in a similar fashion. Second, we propose word relation shift to analyze how the relationship between two words has changed over time. As a test case, we investigate the word privacy (and related words identified by a pre-existing dictionary), as an example of a word that has shifted semantics historically and remains vibrantly explored as a concept in contemporary humanistic discourse. We report that the term privacy in comparison shows relatively little change initially – with correlation analysis revealing more about how key terms surrounding privacy have shifted in tandem, and explore nuanced changes through word pair analysis, suggesting a shift toward concreteness in particular.
| Original language | English |
|---|---|
| Pages | 461-474 |
| Number of pages | 14 |
| Publication status | Published - 2023 |
| Event | 2023 Computational Humanities Research Conference, CHR 2023 - Paris, France Duration: 6 Dec 2023 → 8 Dec 2023 |
Conference
| Conference | 2023 Computational Humanities Research Conference, CHR 2023 |
|---|---|
| Country/Territory | France |
| City | Paris |
| Period | 6/12/2023 → 8/12/2023 |
Keywords
- computational semantics
- language models
- semantic change