Name
Abstract | ||
|---|---|---|
Zero-shot slot filling has received considerable attention to cope with the problem of limited available data for the target domain. One of the important factors in zero-shot learning is to make the model learn generalized and reliable representations. For this purpose, we present mcBERT, which stands for momentum contrastive learning with BERT, to develop a robust zero-shot slot filling model. mcBERT uses BERT to initialize the two encoders, the query encoder and key encoder, and is trained by applying momentum contrastive learning. Our experimental results on the SNIPS benchmark show that mcBERT substantially outperforms the previous models, recording a new state-of-the-art. Besides, we also show that each component composing mcBERT contributes to the performance improvement. |
Year | DOI | Venue |
|---|---|---|
2022 | 10.21437/INTERSPEECH.2022-839 | Conference of the International Speech Communication Association (INTERSPEECH) |
DocType | Citations | PageRank |
Conference | 0 | 0.34 |
References | Authors | |
0 | 3 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Seong-Hwan Heo | 1 | 0 | 0.34 |
| WonKee Lee | 2 | 0 | 0.68 |
| Jong-Hyeok Lee | 3 | 740 | 97.88 |