Papers by Göran Kauermann
Embedding Space Correlation as a Measure of Domain Similarity (2020.lrec-1)
Copied to clipboard
| Challenge: | Existing work on domain similarity using text-based features of corpus is limited by pre-trained word embeddings. |
| Approach: | They propose a measure of domain similarity based on dimension-wise correlations between embedding spaces . they find a threshold at which the measure indicates that two corpora come from the same domain . |
| Outcome: | The proposed measure can be used to determine which corpora are more similar to each other in a cross-domain sentiment detection task. |