Contextualized embeddings for semantic change detection: Lessons learned
We present a qualitative analysis of the (potentially erroneous) outputs of contextualized embedding-based methods for detecting diachronic semantic change. First, we introduce an ensemble method outperforming previously described contextualized approaches. This method is used as a basis for an in-...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Linköping University Electronic Press
2022-08-01
|
| Series: | Northern European Journal of Language Technology |
| Online Access: | https://nejlt.ep.liu.se/article/view/3478 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832591216157392896 |
|---|---|
| author | Andrey Kutuzov Erik Velldal Lilja Øvrelid |
| author_facet | Andrey Kutuzov Erik Velldal Lilja Øvrelid |
| author_sort | Andrey Kutuzov |
| collection | DOAJ |
| description |
We present a qualitative analysis of the (potentially erroneous) outputs of contextualized embedding-based methods for detecting diachronic semantic change. First, we introduce an ensemble method outperforming previously described contextualized approaches. This method is used as a basis for an in-depth analysis of the degrees of semantic change predicted for English words across 5 decades. Our findings show that contextualized methods can often predict high change scores for words which are not undergoing any real diachronic semantic shift in the lexicographic sense of the term (or at least the status of these shifts is questionable). Such challenging cases are discussed in detail with examples, and their linguistic categorization is proposed. Our conclusion is that pre-trained contextualized language models are prone to confound changes in lexicographic senses and changes in contextual variance, which naturally stem from their distributional nature, but is different from the types of issues observed in methods based on static embeddings. Additionally, they often merge together syntactic and semantic aspects of lexical entities. We propose a range of possible future solutions to these issues.
|
| format | Article |
| id | doaj-art-232869529e3a4d5a9311658eb3893cda |
| institution | Kabale University |
| issn | 2000-1533 |
| language | English |
| publishDate | 2022-08-01 |
| publisher | Linköping University Electronic Press |
| record_format | Article |
| series | Northern European Journal of Language Technology |
| spelling | doaj-art-232869529e3a4d5a9311658eb3893cda2025-01-22T15:25:17ZengLinköping University Electronic PressNorthern European Journal of Language Technology2000-15332022-08-018110.3384/nejlt.2000-1533.2022.3478Contextualized embeddings for semantic change detection: Lessons learnedAndrey Kutuzov0Erik Velldal1Lilja Øvrelid2University of OsloUniversity of OsloUniversity of Oslo We present a qualitative analysis of the (potentially erroneous) outputs of contextualized embedding-based methods for detecting diachronic semantic change. First, we introduce an ensemble method outperforming previously described contextualized approaches. This method is used as a basis for an in-depth analysis of the degrees of semantic change predicted for English words across 5 decades. Our findings show that contextualized methods can often predict high change scores for words which are not undergoing any real diachronic semantic shift in the lexicographic sense of the term (or at least the status of these shifts is questionable). Such challenging cases are discussed in detail with examples, and their linguistic categorization is proposed. Our conclusion is that pre-trained contextualized language models are prone to confound changes in lexicographic senses and changes in contextual variance, which naturally stem from their distributional nature, but is different from the types of issues observed in methods based on static embeddings. Additionally, they often merge together syntactic and semantic aspects of lexical entities. We propose a range of possible future solutions to these issues. https://nejlt.ep.liu.se/article/view/3478 |
| spellingShingle | Andrey Kutuzov Erik Velldal Lilja Øvrelid Contextualized embeddings for semantic change detection: Lessons learned Northern European Journal of Language Technology |
| title | Contextualized embeddings for semantic change detection: Lessons learned |
| title_full | Contextualized embeddings for semantic change detection: Lessons learned |
| title_fullStr | Contextualized embeddings for semantic change detection: Lessons learned |
| title_full_unstemmed | Contextualized embeddings for semantic change detection: Lessons learned |
| title_short | Contextualized embeddings for semantic change detection: Lessons learned |
| title_sort | contextualized embeddings for semantic change detection lessons learned |
| url | https://nejlt.ep.liu.se/article/view/3478 |
| work_keys_str_mv | AT andreykutuzov contextualizedembeddingsforsemanticchangedetectionlessonslearned AT erikvelldal contextualizedembeddingsforsemanticchangedetectionlessonslearned AT liljaøvrelid contextualizedembeddingsforsemanticchangedetectionlessonslearned |