Abstract | ||
---|---|---|
We address the task of unsupervised Semantic Textual Similarity (STS) by ensembling diverse pre-trained sentence encoders into sentence meta-embeddings. We apply and extend different meta-embedding methods from the word embedding literature, including dimensionality reduction (Yin and Sch\"utze, 2016), generalized Canonical Correlation Analysis (Rastogi et al., 2015) and cross-view autoencoders (Bollegala and Bao, 2018). We set a new unsupervised State of The Art (SoTA) on the STS Benchmark and on the STS12-STS16 datasets, with gains of between 3.7% and 6.4% Pearson's r over single-source systems. |
Year | DOI | Venue |
---|---|---|
2020 | 10.5282/UBM/EPUB.72194 | ACL |
DocType | Volume | Citations |
Conference | 2020.acl-main | 0 |
PageRank | References | Authors |
0.34 | 0 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Nina Poerner | 1 | 0 | 1.35 |
Ulli Waltinger | 2 | 64 | 10.76 |
Hinrich Schütze | 3 | 2113 | 362.21 |