Transparent Semantic Change Detection with Dependency-Based Profiles
For researchers in computational linguistics, this work offers a transparent alternative to opaque neural methods for semantic change detection, though it is incremental as it applies existing dependency features to a known task.
The paper proposes a dependency-based method for lexical semantic change detection that outperforms several neural embedding-based models, achieving strong performance on LSC benchmarks while providing interpretable predictions.
Most modern computational approaches to lexical semantic change detection (LSC) rely on embedding-based distributional word representations with neural networks. Despite the strong performance on LSC benchmarks, they are often opaque. We investigate an alternative method which relies purely on dependency co-occurrence patterns of words. We demonstrate that it is effective for semantic change detection and even outperforms a number of distributional semantic models. We provide an in-depth quantitative and qualitative analysis of the predictions, showing that they are plausible and interpretable.