ASC (TIL, 19 tasks) (Task Incremental Aspect Sentiment Classification)
Introduced by Ke et al. in Adapting BERT for Continual Learning of a Sequence of Aspect Sentiment Classification Tasks
A set of 19 ASC datasets (reviews of 19 products) producing a sequence of 19 tasks. Each dataset represents a task. The datasets are from 4 sources: (1) HL5Domains (Hu and Liu, 2004) with reviews of 5 products; (2) Liu3Domains (Liu et al., 2015) with reviews of 3 products; (3) Ding9Domains (Ding et al., 2008) with reviews of 9 products; and (4) SemEval14 with reviews of 2 products - SemEval 2014 Task 4 for laptop and restaurant. For (1), (2) and (3), we split about 10% of the original data as the validate data, another about 10% of the original data as the testing data. For (4), We use 150 examples from the training set for validation. To be consistent with existing research(Tang et al., 2016), examples belonging to the conflicting polarity (both positive and negative sentiments are expressed about an aspect term) are not used. Statistics and details of the 19 datasets are given on Page https://github.com/ZixuanKe/PyContinual.
Benchmarks
| Trend | Task | Dataset Variant | Best Model | Paper | Code |
|---|---|---|---|---|---|
|
ASC (19 tasks)
|
Multi-task Learning
|
Papers
| Paper | Code | Results | Date | Stars |
|---|
